© 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. 87596
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
    ÃĤ
    -0.10
    ;.
    -0.10
     manip
    -0.10
    itto
    -0.10
     froze
    -0.10
    HITE
    -0.09
    .rt
    -0.09
    sse
    -0.09
     compliments
    -0.09
    elp
    -0.09
    POSITIVE LOGITS
     Arcade
    0.09
    anus
    0.09
    Ļ¨
    0.09
    unal
    0.08
    à¹Į
    0.08
    .properties
    0.08
     Marr
    0.08
     Jarvis
    0.08
    ibu
    0.08
     sublic
    0.07
    Activations Density 0.001%

    No Known Activations