Circuit-Tracer: A New Library for Finding Feature Circuits

Michael Hanna, Mateusz Piotrowski, Jack Lindsey, Emmanuel Ameisen


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.
Anthology ID:
2025.blackboxnlp-1.14
Volume:
Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Yonatan Belinkov, Aaron Mueller, Najoung Kim, Hosein Mohebbi, Hanjie Chen, Dana Arad, Gabriele Sarti
Venues:
BlackboxNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
239–249
Language:
URL:
https://aclanthology.org/2025.blackboxnlp-1.14/
DOI:
Bibkey:
Cite (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.
Cite (Informal):
Circuit-Tracer: A New Library for Finding Feature Circuits (Hanna et al., BlackboxNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.blackboxnlp-1.14.pdf