© 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. 46062
    Prev
    Next
    INDEX
    Explanations

    eyebrows or championship titles

    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
    ･･
    -0.13
     Din
    -0.12
     Lung
    -0.12
    [table
    -0.12
    giene
    -0.11
     Warm
    -0.11
    REA
    -0.11
    -exc
    -0.11
     Palest
    -0.11
    Echo
    -0.11
    POSITIVE LOGITS
     eyebrow
    0.12
     questioning
    0.11
     querying
    0.09
     dubious
    0.09
     skeptical
    0.09
     skept
    0.08
     ridge
    0.08
     questionable
    0.08
     challeng
    0.08
     question
    0.08
    Activations Density 0.002%

    No Known Activations