© 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. 18745
    Prev
    Next
    INDEX
    Explanations

    movie reviews

    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
     Getty
    -0.09
     lateral
    -0.08
    lier
    -0.08
     reconciliation
    -0.08
     reconc
    -0.08
    ukan
    -0.08
    -Sah
    -0.08
    _quiz
    -0.08
     Lima
    -0.08
    onga
    -0.08
    POSITIVE LOGITS
     reviews
    0.66
     review
    0.65
     reviewer
    0.61
     reviewers
    0.58
     reviewing
    0.57
     Review
    0.56
     Reviews
    0.55
    review
    0.54
     reviewed
    0.54
    -review
    0.54
    Activations Density 0.730%

    No Known Activations