© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46739
    Prev
    Next
    INDEX
    Explanations

    terms of the Apache License

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —he
    -0.10
    ิ
    -0.10
    Ñij
    -0.09
    Ù
    -0.09
     ALSO
    -0.09
    —we
    -0.09
    ”—
    -0.08
     Holt
    -0.08
     dept
    -0.08
    Æ°á»
    -0.08
    POSITIVE LOGITS
    ofi
    0.10
     âĢİ
    0.09
    *',
    0.09
    *",
    0.09
    ombo
    0.09
     Mor
    0.08
    :↵↵↵↵
    0.08
    <|fim_middle|>
    0.08
     Dak
    0.08
     Neil
    0.08
    Activations Density 0.002%

    No Known Activations