© 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. 50288
    Prev
    Next
    INDEX
    Explanations

    media types (anime, manga, movies, games)

    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
     neur
    -0.10
     lux
    -0.09
     amazon
    -0.08
    yal
    -0.08
    anh
    -0.08
     FAQ
    -0.08
     reception
    -0.07
     recl
    -0.07
     thr
    -0.07
     Authentication
    -0.07
    POSITIVE LOGITS
     manga
    0.20
     movies
    0.19
     anime
    0.18
     Manga
    0.18
     videog
    0.17
    movies
    0.16
     comics
    0.16
     Movies
    0.16
     movie
    0.15
     animation
    0.15
    Activations Density 0.245%

    No Known Activations