© 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. 117377
    Prev
    Next
    INDEX
    Explanations

    colon, cialis, omega, sort, list, assert

    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
    <|fim_middle|>
    -0.13
     ÂŃ
    -0.10
     jew
    -0.09
     darn
    -0.09
     accom
    -0.09
     —
    -0.09
     dort
    -0.09
     loosely
    -0.09
    hire
    -0.09
     âĢ¦.
    -0.08
    POSITIVE LOGITS
    dic
    0.09
    /ne
    0.09
    AFF
    0.08
    (ne
    0.08
     Gra
    0.08
    @Table
    0.08
    urg
    0.08
     Aph
    0.08
     Lyn
    0.08
     rh
    0.08
    Activations Density 0.033%

    No Known Activations