© 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. 33575
    Prev
    Next
    INDEX
    Explanations

    physical activity and health benefits

    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
     reass
    -0.08
     molest
    -0.07
     disin
    -0.07
     bait
    -0.07
    beb
    -0.07
    reb
    -0.07
     dem
    -0.07
     sensit
    -0.06
     catering
    -0.06
     perce
    -0.06
    POSITIVE LOGITS
     exercise
    0.22
     Regular
    0.22
     regular
    0.21
     laughter
    0.21
    Regular
    0.21
     regularly
    0.20
     Exercise
    0.19
     exercising
    0.19
    Exercise
    0.19
    exercise
    0.18
    Activations Density 0.267%

    No Known Activations