© 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. 90790
    Prev
    Next
    INDEX
    Explanations

    forum posts metadata

    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
     comments
    -0.12
    brig
    -0.11
     category
    -0.11
     comment
    -0.11
    comments
    -0.10
     commenter
    -0.10
     Comments
    -0.10
     COMMENTS
    -0.10
     outnumber
    -0.10
     tags
    -0.10
    POSITIVE LOGITS
     Pais
    0.12
    Edited
    0.11
     Extras
    0.10
     Pivot
    0.10
     Reign
    0.10
     chrome
    0.10
    ystone
    0.10
    wins
    0.09
     Chrom
    0.09
    unread
    0.09
    Activations Density 0.192%

    No Known Activations