© 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. 46052
    Prev
    Next
    INDEX
    Explanations

    Woody Allen and future

    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
    Negative Logits
     Kö
    -0.08
     nostalg
    -0.07
     minut
    -0.06
     kosher
    -0.06
    <|fim_middle|>
    -0.06
     Mold
    -0.06
    ByPrimaryKey
    -0.06
     excell
    -0.06
    OrUpdate
    -0.06
     impres
    -0.06
    POSITIVE LOGITS
    oce
    0.09
    avs
    0.08
     sca
    0.08
    EFR
    0.08
    assen
    0.08
    ода
    0.08
     Unsure
    0.08
     Gab
    0.08
    uchen
    0.08
     Lingu
    0.08
    Activations Density 10.069%

    No Known Activations