© 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. 116898
    Prev
    Next
    INDEX
    Explanations

    .com/.ph or FightBackNews

    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
     frac
    -0.09
    WND
    -0.09
    kur
    -0.09
     Burl
    -0.09
     Lehr
    -0.08
    ç¤
    -0.08
    riba
    -0.08
    .openg
    -0.08
     erot
    -0.08
    ellig
    -0.08
    POSITIVE LOGITS
    á»ĩn
    0.09
     Pill
    0.09
     Emm
    0.08
     Plain
    0.08
     Monter
    0.08
    -ish
    0.08
    zon
    0.08
    eph
    0.08
     ugly
    0.08
    lac
    0.08
    Activations Density 0.002%

    No Known Activations