© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87950
    Prev
    Next
    INDEX
    Explanations

    mathematical derivatives or code structure

    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
    ikan
    -0.10
     -,
    -0.09
     «
    -0.09
     Â
    -0.09
     ().
    -0.09
     ``
    -0.08
     Chatt
    -0.08
     Mond
    -0.08
     -.
    -0.07
     Bez
    -0.07
    POSITIVE LOGITS
    "↵↵
    0.11
     cum
    0.11
     commande
    0.10
     asshole
    0.10
     FUCK
    0.10
     cunt
    0.10
    !"↵↵
    0.10
     pussy
    0.10
    ">↵↵
    0.10
    **↵↵
    0.10
    Activations Density 0.026%

    No Known Activations