© 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. 111565
    Prev
    Next
    INDEX
    Explanations

    exclamations of surprise or strong reaction

    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
    ropp
    -0.10
    661
    -0.09
     AO
    -0.09
     ffm
    -0.09
    /MIT
    -0.09
     Sullivan
    -0.09
     seat
    -0.09
    acb
    -0.08
    ooks
    -0.08
     Schro
    -0.08
    POSITIVE LOGITS
     okay
    0.12
     bold
    0.11
     OK
    0.11
    Bold
    0.11
    quet
    0.11
     harsh
    0.10
    OK
    0.10
     Bold
    0.10
     sounds
    0.10
     somehow
    0.10
    Activations Density 0.012%

    No Known Activations