© 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. 90017
    Prev
    Next
    INDEX
    Explanations

    coffee shop cafe

    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
     whiskey
    -0.18
     alcohol
    -0.18
     dinner
    -0.17
     tonight
    -0.17
     drunken
    -0.17
     Alcohol
    -0.16
     vodka
    -0.16
     nightclub
    -0.16
     drunk
    -0.16
     cocktail
    -0.16
    POSITIVE LOGITS
     Starbucks
    0.31
     coffee
    0.28
     Coffee
    0.27
     cafe
    0.26
     café
    0.25
    Coffee
    0.23
     cafes
    0.23
    coffee
    0.22
     espresso
    0.22
     Cafe
    0.22
    Activations Density 0.124%

    No Known Activations