© 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. 3548
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion

    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
     Gan
    -0.09
     Clover
    -0.09
     Richards
    -0.09
     camb
    -0.09
    _bulk
    -0.08
    fc
    -0.08
    -secondary
    -0.08
     pier
    -0.08
     reacted
    -0.08
     neighborhood
    -0.08
    POSITIVE LOGITS
     smile
    0.22
     sigh
    0.17
     grin
    0.17
     smirk
    0.16
     flourish
    0.16
     laugh
    0.15
     smiles
    0.14
     Smile
    0.14
     chuck
    0.13
     voice
    0.12
    Activations Density 0.011%

    No Known Activations