© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113958
    Prev
    Next
    INDEX
    Explanations

    chart, diagram, list, written product

    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
    iban
    -0.08
     ripe
    -0.08
     voyeur
    -0.08
     swiftly
    -0.08
     defaults
    -0.08
     hinted
    -0.08
     Hun
    -0.07
    .uni
    -0.07
     native
    -0.07
     peek
    -0.07
    POSITIVE LOGITS
     charts
    0.26
     diagram
    0.26
     chart
    0.25
     diagrams
    0.25
     lists
    0.24
     spreadsheet
    0.24
     written
    0.24
     list
    0.24
     checklist
    0.22
     PowerPoint
    0.21
    Activations Density 0.474%

    No Known Activations