© 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. 91527
    Prev
    Next
    INDEX
    Explanations

    book titles or album names

    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
     Andersen
    -0.08
     Andrea
    -0.08
     lone
    -0.07
     Whit
    -0.07
     Salem
    -0.07
    pls
    -0.07
     Sevent
    -0.07
     barg
    -0.07
    XL
    -0.07
    ilden
    -0.07
    POSITIVE LOGITS
     upp
    0.08
    ulario
    0.08
     Cly
    0.08
    contri
    0.08
    anke
    0.08
     Wort
    0.08
    ï¿¥
    0.08
    hwnd
    0.08
    dition
    0.07
     Ber
    0.07
    Activations Density 3.514%

    No Known Activations