© 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. 115768
    Prev
    Next
    INDEX
    Explanations

    supplies and food

    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
    .ov
    -0.11
     knobs
    -0.10
     accents
    -0.10
    ève
    -0.10
     bubbles
    -0.09
    ynet
    -0.09
    hair
    -0.09
     taxing
    -0.09
     rims
    -0.09
    het
    -0.09
    POSITIVE LOGITS
     food
    0.30
     supplies
    0.29
     FOOD
    0.23
    food
    0.23
     Food
    0.22
     stocked
    0.21
     provisions
    0.21
     Supplies
    0.21
    -food
    0.21
    Food
    0.21
    Activations Density 0.161%

    No Known Activations