© 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. 87885
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

    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
     specialties
    -0.10
    Liked
    -0.10
     whom
    -0.10
     messages
    -0.09
    utz
    -0.09
    ulong
    -0.09
     beneficiary
    -0.09
     UID
    -0.09
    oord
    -0.09
     trap
    -0.09
    POSITIVE LOGITS
     Toll
    0.13
     +(
    0.12
     +
    0.10
     Blaze
    0.09
     info
    0.09
    sales
    0.09
     Sales
    0.09
     toll
    0.09
    lice
    0.09
    +(
    0.09
    Activations Density 0.088%

    No Known Activations