© 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. 116379
    Prev
    Next
    INDEX
    Explanations

    passer, passersby, passer rating

    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
     Hav
    -0.12
     Hills
    -0.11
    yh
    -0.11
    otel
    -0.11
     resorts
    -0.11
     Farr
    -0.10
    enerator
    -0.10
    foon
    -0.10
    /use
    -0.10
    iest
    -0.10
    POSITIVE LOGITS
     passer
    0.11
     Rip
    0.08
     Pick
    0.08
     Linden
    0.08
     bystand
    0.08
     walking
    0.08
     acquaintance
    0.07
     speeding
    0.07
     Dover
    0.07
    obs
    0.07
    Activations Density 0.001%

    No Known Activations