© 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. 47432
    Prev
    Next
    INDEX
    Explanations

    physical activity and symptoms

    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
     suction
    -0.11
     practise
    -0.11
     vocal
    -0.10
    iete
    -0.10
     weighted
    -0.10
     spas
    -0.10
     coaching
    -0.10
     diet
    -0.10
     practice
    -0.09
     Kawasaki
    -0.09
    POSITIVE LOGITS
     sweat
    0.12
     Aer
    0.12
     inv
    0.11
     burning
    0.11
     end
    0.10
     aer
    0.10
     Inv
    0.10
     sweating
    0.10
     Sweat
    0.10
     oxygen
    0.09
    Activations Density 0.344%

    No Known Activations