© 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. 30697
    Prev
    Next
    INDEX
    Explanations

    media type (movie, book, film)

    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
    indy
    -0.09
    /Instruction
    -0.08
     inher
    -0.08
    ahu
    -0.08
    asha
    -0.08
    /host
    -0.08
    yc
    -0.08
    atak
    -0.08
     unrest
    -0.07
    .Setup
    -0.07
    POSITIVE LOGITS
    /book
    0.18
    /movie
    0.18
    /books
    0.13
     title
    0.13
     makers
    0.13
    ends
    0.12
     titles
    0.12
     protagonists
    0.12
    /article
    0.12
     reviewer
    0.12
    Activations Density 0.275%

    No Known Activations