© 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. 15097
    Prev
    Next
    INDEX
    Explanations

    photo captions and citations

    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
    uther
    -0.10
     Loving
    -0.10
     ultr
    -0.09
     Walls
    -0.09
     privat
    -0.08
     Iss
    -0.08
     Laugh
    -0.08
     Sunrise
    -0.08
     Fits
    -0.08
    olver
    -0.08
    POSITIVE LOGITS
     (...)
    0.09
    ingly
    0.09
     ¿
    0.09
    BILE
    0.09
     Sara
    0.09
    oco
    0.08
     plain
    0.08
    ofi
    0.08
     impacted
    0.08
    HEMA
    0.08
    Activations Density 0.001%

    No Known Activations