<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-luca-2026-embedding">
    <titleInfo>
        <title>Embedding Orrery: Visual Exploration of Embedding Spaces and Sparse Autoencoder Features</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Giacomo</namePart>
        <namePart type="family">De Luca</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sweta</namePart>
            <namePart type="family">Agrawal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alberto</namePart>
            <namePart type="family">Abad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-461-3</identifier>
    </relatedItem>
    <abstract>Embedding Orrery is an open-source platform for interactive 3-dimensional visualization of embedding spaces, with native support for Sparse Autoencoders (SAEs), built for data exploration and interpretability research. Given any textual, image, or vector dataset, a single pipeline - embedding, projection, clustering, automatic topic labeling and, optionally, the collection of per-document SAE feature activations - turns it into a 3D constellation that can be searched visually, semantically, lexically, or by SAE feature names; probes can be trained, configured and scored directly in the interface. SAEs are automatically downloaded and rendered as navigable constellations in which entering a prompt highlights the features it activates. Individual features can be inspected inside a dashboard and injected into the model for causal steering. The star-cartography-inspired interface sustains up to 500,000 points, including WebGL animations and volumetric nebula shaders, on 8 GB of RAM. Embedding Orrery is released under the Apache 2.0 license. Code: https://github.com/Giacomo-De-Luca/embedding-orrery. HF Spaces: https://huggingface.co/spaces/GiacomoDeLuca/orrery-demo.</abstract>
    <identifier type="citekey">de-luca-2026-embedding</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-demos.68/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>717</start>
            <end>727</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Embedding Orrery: Visual Exploration of Embedding Spaces and Sparse Autoencoder Features
%A De Luca, Giacomo
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F de-luca-2026-embedding
%X Embedding Orrery is an open-source platform for interactive 3-dimensional visualization of embedding spaces, with native support for Sparse Autoencoders (SAEs), built for data exploration and interpretability research. Given any textual, image, or vector dataset, a single pipeline - embedding, projection, clustering, automatic topic labeling and, optionally, the collection of per-document SAE feature activations - turns it into a 3D constellation that can be searched visually, semantically, lexically, or by SAE feature names; probes can be trained, configured and scored directly in the interface. SAEs are automatically downloaded and rendered as navigable constellations in which entering a prompt highlights the features it activates. Individual features can be inspected inside a dashboard and injected into the model for causal steering. The star-cartography-inspired interface sustains up to 500,000 points, including WebGL animations and volumetric nebula shaders, on 8 GB of RAM. Embedding Orrery is released under the Apache 2.0 license. Code: https://github.com/Giacomo-De-Luca/embedding-orrery. HF Spaces: https://huggingface.co/spaces/GiacomoDeLuca/orrery-demo.
%U https://aclanthology.org/2026.emnlp-demos.68/
%P 717-727

Markdown (Informal)

[Embedding Orrery: Visual Exploration of Embedding Spaces and Sparse Autoencoder Features](https://aclanthology.org/2026.emnlp-demos.68/) (De Luca, EMNLP 2026)

• Embedding Orrery: Visual Exploration of Embedding Spaces and Sparse Autoencoder Features (De Luca, EMNLP 2026)

ACL

• Giacomo De Luca. 2026. Embedding Orrery: Visual Exploration of Embedding Spaces and Sparse Autoencoder Features. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 717–727, Budapest, Hungary. Association for Computational Linguistics.