© 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. 112408
    Prev
    Next
    INDEX
    Explanations

    groin/crotch, Rochester, Corp

    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
    o
    -0.13
    aar
    -0.12
    a
    -0.12
    aab
    -0.12
    erate
    -0.12
    er
    -0.11
    s
    -0.11
     cascade
    -0.10
    auction
    -0.10
    vers
    -0.10
    POSITIVE LOGITS
     area
    0.16
     region
    0.13
    area
    0.11
    -area
    0.11
    shield
    0.10
    /front
    0.10
    -level
    0.10
    iful
    0.09
    ety
    0.09
    éĥ¨
    0.08
    Activations Density 0.001%

    No Known Activations