© 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. 49899
    Prev
    Next
    INDEX
    Explanations

    watching movies, television, films

    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
    olib
    -0.09
    shares
    -0.08
    ĵį
    -0.08
    apan
    -0.08
     intents
    -0.08
    aterno
    -0.08
     unm
    -0.08
    Deleted
    -0.08
     decre
    -0.08
    orda
    -0.08
    POSITIVE LOGITS
     movies
    0.46
     Movies
    0.38
     TV
    0.35
     television
    0.35
     films
    0.35
     movie
    0.35
     Hollywood
    0.34
    Movies
    0.32
     tv
    0.30
    movies
    0.29
    Activations Density 0.292%

    No Known Activations