© 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. 25331
    Prev
    Next
    INDEX
    Explanations

    parse variations

    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
    cko
    -0.10
    uring
    -0.10
    vent
    -0.10
    venge
    -0.10
     Dew
    -0.09
     Laguna
    -0.09
    icina
    -0.09
    ical
    -0.09
    aurant
    -0.09
    ĩ
    -0.09
    POSITIVE LOGITS
    parse
    0.12
     Parse
    0.11
     parsed
    0.10
    _qs
    0.10
    .parse
    0.10
     parsing
    0.10
     parser
    0.10
     parse
    0.10
     parses
    0.10
     ParseException
    0.09
    Activations Density 0.067%

    No Known Activations