© 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. 25118
    Prev
    Next
    INDEX
    Explanations

    track record or listing

    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
     absorbing
    -0.07
    gr
    -0.07
    est
    -0.07
     Cooke
    -0.07
     Hammond
    -0.07
    ovich
    -0.06
    omer
    -0.06
    297
    -0.06
    ubb
    -0.06
    |[
    -0.06
    POSITIVE LOGITS
     track
    0.22
    -track
    0.20
     Track
    0.20
    track
    0.19
    .Track
    0.18
     tracks
    0.18
    .track
    0.17
    (track
    0.17
     Tracks
    0.17
     record
    0.16
    Activations Density 0.020%

    No Known Activations