© 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. 33429
    Prev
    Next
    INDEX
    Explanations

    .html/.php/.aspx 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
    cot
    -0.06
    anske
    -0.06
     continually
    -0.06
     constituents
    -0.06
    ATRIX
    -0.06
    /Grid
    -0.06
     Crowley
    -0.06
    dess
    -0.06
     Kontakt
    -0.06
     subdivision
    -0.06
    POSITIVE LOGITS
    .html
    0.32
    .aspx
    0.26
    .htm
    0.25
    %C
    0.24
    .xhtml
    0.19
    .shtml
    0.19
    ?page
    0.18
    .Html
    0.17
    .ht
    0.17
    .md
    0.17
    Activations Density 0.438%

    No Known Activations