© 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. 25539
    Prev
    Next
    INDEX
    Explanations

    hunger and appetite

    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
     relax
    -0.14
     relaxation
    -0.14
     Relax
    -0.13
     relaxing
    -0.12
     leisure
    -0.11
    dish
    -0.11
     relaxed
    -0.11
     table
    -0.11
     dish
    -0.11
    EFF
    -0.10
    POSITIVE LOGITS
     hunger
    0.47
     hungry
    0.42
     Hunger
    0.39
     starving
    0.37
     starvation
    0.35
     appetite
    0.28
     famine
    0.28
     thirst
    0.26
     Hung
    0.26
    hung
    0.25
    Activations Density 0.272%

    No Known Activations