© 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. 87930
    Prev
    Next
    INDEX
    Explanations

    hundreds of

    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
    wis
    -0.11
    gers
    -0.10
     entirety
    -0.10
    etas
    -0.09
     Stadt
    -0.09
    berra
    -0.09
    ernet
    -0.09
    w
    -0.09
    Hunter
    -0.09
    PRETTY
    -0.09
    POSITIVE LOGITS
    fold
    0.12
     thousands
    0.11
     Thousands
    0.10
    -fold
    0.09
     hundreds
    0.09
    —even
    0.09
     of
    0.09
    ìĸ
    0.09
    /th
    0.09
     thousand
    0.09
    Activations Density 0.024%

    No Known Activations