© 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. 4903
    Prev
    Next
    INDEX
    Explanations

    milk and dairy products

    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
     poker
    -0.12
     explosives
    -0.12
     diamond
    -0.12
     Poker
    -0.11
     sand
    -0.11
    /hash
    -0.11
     gem
    -0.11
     Rocks
    -0.11
     gravel
    -0.10
     piled
    -0.10
    POSITIVE LOGITS
     milk
    0.57
     Milk
    0.53
     dairy
    0.48
     lact
    0.47
     Dairy
    0.44
     mil
    0.30
     breastfeeding
    0.29
     Milky
    0.29
     cows
    0.29
    ilk
    0.26
    Activations Density 0.324%

    No Known Activations