© 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. 92416
    Prev
    Next
    INDEX
    Explanations

    Clapton, Clémente, Clouston, Clenbuterol

    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
    /client
    -0.14
    opal
    -0.11
    aging
    -0.09
    ogl
    -0.09
    itary
    -0.09
    inia
    -0.09
    iom
    -0.09
    anes
    -0.09
    agini
    -0.09
    oit
    -0.09
    POSITIVE LOGITS
    voy
    0.14
    ifton
    0.12
    mate
    0.12
    ément
    0.12
    arity
    0.11
    /cl
    0.11
    audio
    0.11
    æĪ·
    0.11
     Cl
    0.11
    æ¥
    0.11
    Activations Density 0.435%

    No Known Activations