© 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. 7762
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    ALA
    -0.11
     Anal
    -0.10
     admir
    -0.10
     Demon
    -0.10
    ware
    -0.10
     ($(
    -0.10
     Surv
    -0.10
    lest
    -0.10
    utch
    -0.10
     rendition
    -0.10
    POSITIVE LOGITS
    \↵
    0.07
     Apartment
    0.07
     Kosten
    0.07
     paraph
    0.07
    onio
    0.07
     metro
    0.07
    UNT
    0.07
     Startup
    0.07
     extrem
    0.07
    enso
    0.07
    Activations Density 0.055%

    No Known Activations