© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114620
    Prev
    Next
    INDEX
    Explanations

    sip, drink, or beverage

    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
     seeding
    -0.12
     vaginal
    -0.10
     rent
    -0.10
     tangled
    -0.10
     breadcrumb
    -0.09
     Kis
    -0.09
    Rent
    -0.09
     Entr
    -0.09
     potatoes
    -0.09
     hashing
    -0.09
    POSITIVE LOGITS
     sip
    0.41
     drink
    0.38
     drinking
    0.34
     drank
    0.33
     Drink
    0.33
     thirsty
    0.33
     drinkers
    0.32
     beverage
    0.31
     thirst
    0.31
     Drinking
    0.30
    Activations Density 0.558%

    No Known Activations