© 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. 45983
    Prev
    Next
    INDEX
    Explanations

    Apache License

    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
    ););↵
    -0.10
    )))));č↵
    -0.10
    ByVersion
    -0.10
     dau
    -0.09
    OldData
    -0.09
    .DataTable
    -0.09
     Caj
    -0.09
    owell
    -0.09
    InSection
    -0.08
    rone
    -0.08
    POSITIVE LOGITS
    ">//
    0.11
    Forgot
    0.09
    bios
    0.09
     subs
    0.09
    spe
    0.09
    à¥į
    0.08
    _Post
    0.08
    midd
    0.08
    bild
    0.08
    arial
    0.08
    Activations Density 2.203%

    No Known Activations