© 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. 14056
    Prev
    Next
    INDEX
    Explanations

    millions of people every year

    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
     municipality
    -0.09
     cand
    -0.07
    mond
    -0.07
     meld
    -0.07
    opol
    -0.07
     persist
    -0.07
     monument
    -0.07
    ocio
    -0.07
     tri
    -0.06
     tang
    -0.06
    POSITIVE LOGITS
    ARAM
    0.12
    DEST
    0.11
    isher
    0.11
    ĵį
    0.11
    Toolkit
    0.11
     travellers
    0.11
    ÂĢ
    0.11
     liebe
    0.11
     seks
    0.11
     ski
    0.11
    Activations Density 0.003%

    No Known Activations