© 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. 15223
    Prev
    Next
    INDEX
    Explanations

    Excel spreadsheet data

    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
     intellectual
    -0.09
    Knowledge
    -0.08
     collecting
    -0.08
     Knowledge
    -0.08
     epis
    -0.08
     Museum
    -0.08
     knowledgeable
    -0.08
    -clock
    -0.08
     barber
    -0.08
     quest
    -0.08
    POSITIVE LOGITS
     spreads
    0.23
     spreadsheet
    0.21
     Excel
    0.21
     Spreadsheet
    0.17
     excel
    0.17
     reconc
    0.17
     reconcile
    0.17
     reports
    0.16
    Spread
    0.16
    .xls
    0.16
    Activations Density 0.509%

    No Known Activations