© 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. 92522
    Prev
    Next
    INDEX
    Explanations

    smiling or grinning expressions

    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
     somew
    -0.12
     cabo
    -0.12
     fashioned
    -0.12
    YNAMIC
    -0.12
    /Delete
    -0.11
    illance
    -0.11
     punct
    -0.11
     sounding
    -0.11
     Maz
    -0.11
    CHANT
    -0.11
    POSITIVE LOGITS
     brightly
    0.14
     widely
    0.12
     warmly
    0.12
     broadly
    0.11
     prof
    0.11
     knowingly
    0.11
     sweet
    0.09
     extensively
    0.09
     inward
    0.09
     again
    0.08
    Activations Density 0.002%

    No Known Activations