© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 33219
    Prev
    Next
    INDEX
    Explanations

    code, programming, and technical terms

    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
    )).↵
    -0.09
     loved
    -0.09
    ippo
    -0.09
    ).↵
    -0.09
     discretion
    -0.09
    cer
    -0.08
     ...)↵
    -0.08
    ]).↵
    -0.08
    oui
    -0.08
     payer
    -0.08
    POSITIVE LOGITS
     )[
    0.10
    <thead
    0.09
     psychologically
    0.09
     Dex
    0.09
     Modal
    0.08
    .spotify
    0.08
    chnitt
    0.08
    Saga
    0.08
     Saud
    0.08
     Seks
    0.08
    Activations Density 0.020%

    No Known Activations