© 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. 87744
    Prev
    Next
    INDEX
    Explanations

    punct or punch

    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
    ény
    -0.11
    Markdown
    -0.11
    uales
    -0.10
    edition
    -0.10
     Pur
    -0.10
    wright
    -0.10
    hs
    -0.10
     */↵↵↵↵
    -0.10
    chie
    -0.10
    unn
    -0.10
    POSITIVE LOGITS
     punch
    0.17
     holes
    0.15
     punching
    0.14
     punches
    0.14
     Punch
    0.14
     punched
    0.12
    -hole
    0.11
     drunk
    0.10
    holes
    0.10
    /sl
    0.10
    Activations Density 0.017%

    No Known Activations