© 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. 91322
    Prev
    Next
    INDEX
    Explanations

    Find, Just, Take

    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
     tempor
    -0.09
    ~↵
    -0.09
     Heard
    -0.09
    лиÑĨ
    -0.09
    éĸ
    -0.09
    enville
    -0.09
     supp
    -0.09
     Hearts
    -0.09
    /by
    -0.08
     Eddie
    -0.08
    POSITIVE LOGITS
     womens
    0.09
     courtesy
    0.09
    CED
    0.09
    aint
    0.08
    .experimental
    0.08
    erner
    0.08
    Courtesy
    0.08
     redraw
    0.08
    chy
    0.08
     bright
    0.08
    Activations Density 0.003%

    No Known Activations