© 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. 34243
    Prev
    Next
    INDEX
    Explanations

    web archive URLs

    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
     gloss
    -0.12
    dre
    -0.11
     Gloss
    -0.10
     decals
    -0.10
    synthesize
    -0.10
     unidentified
    -0.10
    sell
    -0.10
    -generic
    -0.10
     Sass
    -0.10
    .reject
    -0.10
    POSITIVE LOGITS
     archive
    0.36
     archived
    0.34
     archival
    0.31
     archives
    0.30
     Archive
    0.30
    .archive
    0.30
    archive
    0.29
    Archive
    0.26
    -archive
    0.26
     arch
    0.25
    Activations Density 0.549%

    No Known Activations