© 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. 91791
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by code entities

    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
     Sylv
    -0.10
     mob
    -0.09
     ConsoleColor
    -0.09
     Stake
    -0.09
    ennis
    -0.08
    LC
    -0.08
    aidu
    -0.08
     tapes
    -0.08
     dow
    -0.08
     calf
    -0.08
    POSITIVE LOGITS
     fav
    0.12
    fav
    0.11
     mature
    0.11
     Autodesk
    0.11
     favor
    0.11
     dig
    0.11
     journals
    0.11
     favored
    0.11
    creativecommons
    0.10
     medals
    0.10
    Activations Density 0.118%

    No Known Activations