© 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. 28729
    Prev
    Next
    INDEX
    Explanations

    image file extensions

    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
     photographers
    -0.11
     PDF
    -0.11
     photographs
    -0.11
     screenshots
    -0.11
     photography
    -0.11
     Wallpaper
    -0.10
     pdf
    -0.10
     Photos
    -0.10
     Photograph
    -0.10
     Benedict
    -0.10
    POSITIVE LOGITS
    .ico
    0.12
    ICO
    0.12
     icon
    0.11
     Bach
    0.11
     emblem
    0.11
    /favicon
    0.11
     transparent
    0.10
     spacer
    0.10
    icon
    0.10
    orda
    0.10
    Activations Density 0.902%

    No Known Activations