© 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. 117109
    Prev
    Next
    INDEX
    Explanations

    racing and races

    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
     Trom
    -0.09
     Playback
    -0.09
     bells
    -0.09
     commute
    -0.09
    æĴŃ
    -0.09
     commuting
    -0.09
     Basketball
    -0.09
     PLAY
    -0.08
     commuter
    -0.08
     hikes
    -0.08
    POSITIVE LOGITS
     racing
    0.38
     Racing
    0.35
     race
    0.33
     racer
    0.33
     NASCAR
    0.31
     races
    0.30
     Race
    0.29
    Race
    0.29
     raced
    0.28
     rac
    0.28
    Activations Density 0.894%

    No Known Activations