© 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. 50824
    Prev
    Next
    INDEX
    Explanations

    singing and performers

    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
     Cheer
    -0.14
     chant
    -0.12
     cheer
    -0.12
     Speakers
    -0.11
     Remix
    -0.10
     deed
    -0.10
     hearing
    -0.10
     Speaker
    -0.10
    urm
    -0.10
     subj
    -0.10
    POSITIVE LOGITS
     passionately
    0.12
     live
    0.11
     covers
    0.11
     vocals
    0.11
     LIVE
    0.10
     suspended
    0.10
     lead
    0.10
     onstage
    0.09
     Powerful
    0.09
     rendition
    0.09
    Activations Density 0.157%

    No Known Activations