© 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. 18390
    Prev
    Next
    INDEX
    Explanations

    json structure identifier

    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
     repl
    -0.07
    987
    -0.07
     correspond
    -0.07
     Prepared
    -0.07
     tai
    -0.07
     orb
    -0.07
    617
    -0.07
    loquent
    -0.07
     promising
    -0.07
     carn
    -0.07
    POSITIVE LOGITS
    ault
    0.11
     Sever
    0.11
     poj
    0.11
    ToF
    0.10
     Clerk
    0.10
    cla
    0.10
     Glyph
    0.10
    strup
    0.10
    iners
    0.10
    won
    0.10
    Activations Density 0.011%

    No Known Activations