@inproceedings{hanna-etal-2025-circuit,
title = "Circuit-Tracer: A New Library for Finding Feature Circuits",
author = "Hanna, Michael and
Piotrowski, Mateusz and
Lindsey, Jack and
Ameisen, Emmanuel",
editor = "Belinkov, Yonatan and
Mueller, Aaron and
Kim, Najoung and
Mohebbi, Hosein and
Chen, Hanjie and
Arad, Dana and
Sarti, Gabriele",
booktitle = "Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.blackboxnlp-1.14/",
pages = "239--249",
ISBN = "979-8-89176-346-3",
abstract = "Feature circuits aim to shed light on LLM behavior by identifying the features that are causally responsible for a given LLM output, and connecting them into a directed graph, or *circuit*, that explains how both each feature and each output arose. However, performing circuit analysis is challenging: the tools for finding, visualizing, and verifying feature circuits are complex and spread across multiple libraries.To facilitate feature-circuit finding, we introduce `circuit-tracer{`}, an open-source library for efficient identification of feature circuits. `circuit-tracer{`} provides an integrated pipeline for finding, visualizing, annotating, and performing interventions on such feature circuits, tested with various model sizes, up to 14B parameters. We make `circuit-tracer{`} available to both developers and end users, via integration with tools such as Neuronpedia, which provides a user-friendly interface."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hanna-etal-2025-circuit">
<titleInfo>
<title>Circuit-Tracer: A New Library for Finding Feature Circuits</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hanna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Piotrowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Lindsey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Ameisen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Najoung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Arad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-346-3</identifier>
</relatedItem>
<abstract>Feature circuits aim to shed light on LLM behavior by identifying the features that are causally responsible for a given LLM output, and connecting them into a directed graph, or *circuit*, that explains how both each feature and each output arose. However, performing circuit analysis is challenging: the tools for finding, visualizing, and verifying feature circuits are complex and spread across multiple libraries.To facilitate feature-circuit finding, we introduce ‘circuit-tracer‘, an open-source library for efficient identification of feature circuits. ‘circuit-tracer‘ provides an integrated pipeline for finding, visualizing, annotating, and performing interventions on such feature circuits, tested with various model sizes, up to 14B parameters. We make ‘circuit-tracer‘ available to both developers and end users, via integration with tools such as Neuronpedia, which provides a user-friendly interface.</abstract>
<identifier type="citekey">hanna-etal-2025-circuit</identifier>
<location>
<url>https://aclanthology.org/2025.blackboxnlp-1.14/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>239</start>
<end>249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Circuit-Tracer: A New Library for Finding Feature Circuits
%A Hanna, Michael
%A Piotrowski, Mateusz
%A Lindsey, Jack
%A Ameisen, Emmanuel
%Y Belinkov, Yonatan
%Y Mueller, Aaron
%Y Kim, Najoung
%Y Mohebbi, Hosein
%Y Chen, Hanjie
%Y Arad, Dana
%Y Sarti, Gabriele
%S Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-346-3
%F hanna-etal-2025-circuit
%X Feature circuits aim to shed light on LLM behavior by identifying the features that are causally responsible for a given LLM output, and connecting them into a directed graph, or *circuit*, that explains how both each feature and each output arose. However, performing circuit analysis is challenging: the tools for finding, visualizing, and verifying feature circuits are complex and spread across multiple libraries.To facilitate feature-circuit finding, we introduce ‘circuit-tracer‘, an open-source library for efficient identification of feature circuits. ‘circuit-tracer‘ provides an integrated pipeline for finding, visualizing, annotating, and performing interventions on such feature circuits, tested with various model sizes, up to 14B parameters. We make ‘circuit-tracer‘ available to both developers and end users, via integration with tools such as Neuronpedia, which provides a user-friendly interface.
%U https://aclanthology.org/2025.blackboxnlp-1.14/
%P 239-249
Markdown (Informal)
[Circuit-Tracer: A New Library for Finding Feature Circuits](https://aclanthology.org/2025.blackboxnlp-1.14/) (Hanna et al., BlackboxNLP 2025)
ACL
- Michael Hanna, Mateusz Piotrowski, Jack Lindsey, and Emmanuel Ameisen. 2025. Circuit-Tracer: A New Library for Finding Feature Circuits. In Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 239–249, Suzhou, China. Association for Computational Linguistics.