© 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. 17974
    Prev
    Next
    INDEX
    Explanations

    code punctuation and structure

    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
    618
    -0.10
     {{{
    -0.09
    (Optional
    -0.09
    //(
    -0.09
     breakdown
    -0.09
    .wik
    -0.09
    laus
    -0.09
    (ph
    -0.09
    inho
    -0.08
    &(
    -0.08
    POSITIVE LOGITS
    etc
    0.09
     sap
    0.08
     accel
    0.08
    inear
    0.08
     snippet
    0.08
     ...)↵
    0.08
     bul
    0.08
     Umb
    0.07
     Vig
    0.07
     serv
    0.07
    Activations Density 0.011%

    No Known Activations