© 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. 92277
    Prev
    Next
    INDEX
    Explanations

    Occidental

    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
    tery
    -0.10
    ishing
    -0.09
    ivre
    -0.09
    365
    -0.09
    chat
    -0.08
     Rossi
    -0.08
    rance
    -0.08
    ingen
    -0.08
     length
    -0.08
     pier
    -0.08
    POSITIVE LOGITS
    ritz
    0.12
    identally
    0.11
    ewan
    0.11
    eten
    0.11
     Fritz
    0.11
     patched
    0.10
    -fire
    0.10
    emachine
    0.10
     flea
    0.10
    asionally
    0.10
    Activations Density 0.009%

    No Known Activations