© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14579
    Prev
    Next
    INDEX
    Explanations

    highcharts, Giving Tuesday, FORTRAN, ALM, Elance, single-cell, United Kingdom

    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
    eid
    -0.10
     Reno
    -0.09
    oshi
    -0.09
     extractor
    -0.09
    sar
    -0.09
    =require
    -0.09
    åijĺ
    -0.09
     formatDate
    -0.09
     comed
    -0.09
     cooks
    -0.09
    POSITIVE LOGITS
    иÑģк
    0.12
    zan
    0.10
     Sou
    0.10
     definit
    0.10
    itag
    0.09
    Sou
    0.09
     sou
    0.09
     Howell
    0.09
     tok
    0.08
    -ever
    0.08
    Activations Density 0.003%

    No Known Activations