© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88343
    Prev
    Next
    INDEX
    Explanations

    movies, actors, actresses, scenes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     unh
    -0.09
    Charts
    -0.09
     phase
    -0.08
     dev
    -0.08
     Heal
    -0.07
     Homer
    -0.07
    _advanced
    -0.07
    dev
    -0.07
     circular
    -0.07
     meetup
    -0.07
    POSITIVE LOGITS
     scenes
    0.13
     prost
    0.13
     extras
    0.13
     credited
    0.12
    credited
    0.12
     actresses
    0.12
    scenes
    0.11
     actors
    0.11
    ubo
    0.11
     Scenes
    0.11
    Activations Density 0.004%

    No Known Activations