© 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. 25845
    Prev
    Next
    INDEX
    Explanations

    alcohol consumption and impairment

    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
     refill
    -0.10
     Cannabis
    -0.10
     Chocolate
    -0.09
     cigarette
    -0.09
     spindle
    -0.09
     heroin
    -0.09
     cigarettes
    -0.09
     yan
    -0.09
     Dynam
    -0.09
     Elastic
    -0.09
    POSITIVE LOGITS
    -dr
    0.12
    |int
    0.11
     imb
    0.11
    IDX
    0.11
    ican
    0.10
    gulp
    0.10
    æİĴ
    0.10
    abo
    0.09
    persona
    0.09
     administr
    0.09
    Activations Density 0.102%

    No Known Activations