© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16140
    Prev
    Next
    INDEX
    Explanations

    watching movies

    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
     backstage
    -0.12
     walking
    -0.11
     walks
    -0.10
     graffiti
    -0.10
     playground
    -0.10
     brief
    -0.10
     roadside
    -0.10
     walker
    -0.10
    -panel
    -0.10
    Walking
    -0.10
    POSITIVE LOGITS
     Netflix
    0.21
     movies
    0.20
     movie
    0.19
     Movies
    0.18
     popcorn
    0.17
     Movie
    0.17
     marathon
    0.17
     DVD
    0.17
     binge
    0.17
     DVDs
    0.17
    Activations Density 0.049%

    No Known Activations