© 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. 87677
    Prev
    Next
    INDEX
    Explanations

    Hollywood entertainment industry

    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
     concert
    -0.10
    government
    -0.10
     government
    -0.10
    coil
    -0.09
     concerts
    -0.09
    marshal
    -0.09
     championship
    -0.09
     demonstr
    -0.09
    gov
    -0.09
    mue
    -0.09
    POSITIVE LOGITS
     Hollywood
    0.29
     industry
    0.20
    ollywood
    0.20
     studios
    0.19
     Industry
    0.18
     Los
    0.17
     nep
    0.17
     studio
    0.17
     Producer
    0.17
     producer
    0.16
    Activations Density 0.272%

    No Known Activations