© 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. 27153
    Prev
    Next
    INDEX
    Explanations

    products and services

    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
     Bes
    -0.10
    icket
    -0.10
     UNICODE
    -0.10
    Bes
    -0.10
     originals
    -0.10
     PIXI
    -0.09
    igli
    -0.09
     multis
    -0.09
     isc
    -0.09
    [next
    -0.09
    POSITIVE LOGITS
     Bark
    0.10
     Flores
    0.09
    ores
    0.09
     Hust
    0.08
     channels
    0.07
    aju
    0.07
     Brick
    0.07
     pack
    0.07
     cave
    0.07
     Outlook
    0.07
    Activations Density 0.001%

    No Known Activations