© 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. 46277
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     invasive
    -0.10
     Alle
    -0.10
     racially
    -0.10
     Kings
    -0.10
    aland
    -0.10
    ^K
    -0.09
     Indo
    -0.09
    assi
    -0.09
     intrusive
    -0.09
    erman
    -0.09
    POSITIVE LOGITS
     Disp
    0.09
    tbody
    0.09
    alah
    0.09
     mercy
    0.09
    otel
    0.09
     mas
    0.09
     Dol
    0.09
     {*}
    0.09
    :)↵
    0.09
     disguised
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.