© 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. 46342
    Prev
    Next
    INDEX
    Explanations

    Board of Immigration Appeals

    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
    (container
    -0.09
     container
    -0.09
    neck
    -0.08
    ovenant
    -0.08
     renegot
    -0.08
     Container
    -0.08
     spins
    -0.08
     cit
    -0.08
    .Volume
    -0.08
    fur
    -0.08
    POSITIVE LOGITS
     boards
    0.29
     board
    0.28
    /board
    0.25
     Boards
    0.25
     Board
    0.24
     BOARD
    0.23
    -board
    0.22
    Board
    0.21
    (board
    0.20
    boards
    0.20
    Activations Density 0.214%

    No Known Activations