© 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. 25671
    Prev
    Next
    INDEX
    Explanations

    subscribe to

    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
     capit
    -0.08
     grat
    -0.08
     smack
    -0.08
    agli
    -0.08
    zens
    -0.08
    lib
    -0.07
    Talk
    -0.07
    tf
    -0.07
    load
    -0.07
    ifi
    -0.07
    POSITIVE LOGITS
     Dayton
    0.11
    bable
    0.11
     Leakage
    0.11
    (Sub
    0.11
     Schneider
    0.11
    /pay
    0.11
     overrun
    0.11
     Hum
    0.11
    DMIN
    0.10
    )\<
    0.10
    Activations Density 0.012%

    No Known Activations