© 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. 15836
    Prev
    Next
    INDEX
    Explanations

    food and eating

    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
    vet
    -0.11
     Pai
    -0.10
     ag
    -0.10
     towels
    -0.10
     multiplic
    -0.10
     ensemble
    -0.10
    ernet
    -0.09
     loose
    -0.09
    /ay
    -0.09
     Ensemble
    -0.09
    POSITIVE LOGITS
     hungry
    0.12
     picnic
    0.12
     starving
    0.11
     munch
    0.11
     nour
    0.10
     hunger
    0.10
    hung
    0.10
     eaten
    0.10
     consumption
    0.09
     consumed
    0.09
    Activations Density 0.111%

    No Known Activations