© 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. 113392
    Prev
    Next
    INDEX
    Explanations

    cocktails and drinks

    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
     food
    -0.14
     drunken
    -0.13
     eating
    -0.13
    food
    -0.12
     pizza
    -0.12
     Food
    -0.11
     Pizza
    -0.11
     ate
    -0.11
     Eating
    -0.11
    Food
    -0.11
    POSITIVE LOGITS
     mart
    0.16
     cocktail
    0.15
     Scotch
    0.15
     cocktails
    0.14
     whisky
    0.13
     Cocktail
    0.13
     glass
    0.13
     gin
    0.13
    mart
    0.12
     chilled
    0.12
    Activations Density 0.068%

    No Known Activations