© 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. 7416
    Prev
    Next
    INDEX
    Explanations

    drinking alcohol or wine

    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
    imei
    -0.10
    uen
    -0.08
     hygiene
    -0.08
     fiat
    -0.08
    ocz
    -0.07
     Williamson
    -0.07
    odus
    -0.07
     predic
    -0.07
     metadata
    -0.07
    peri
    -0.07
    POSITIVE LOGITS
     alcohol
    0.38
     booze
    0.31
     wine
    0.31
     alcoholic
    0.30
     Alcohol
    0.30
     beer
    0.27
     beers
    0.26
     drinks
    0.25
     liquor
    0.25
     drink
    0.25
    Activations Density 0.127%

    No Known Activations