© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92651
    Prev
    Next
    INDEX
    Explanations

    nourishment and energy

    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
    Negative Logits
     indiv
    -0.10
     Crush
    -0.10
     Crushing
    -0.09
     pinch
    -0.09
     Burn
    -0.09
     cook
    -0.09
     overrun
    -0.09
     recipes
    -0.09
    rette
    -0.09
     genu
    -0.09
    POSITIVE LOGITS
     nour
    0.32
     sust
    0.29
     nutrition
    0.22
     replen
    0.20
     hydration
    0.20
     energ
    0.19
     fuel
    0.19
     sustaining
    0.19
     hydrated
    0.19
     energy
    0.19
    Activations Density 0.082%

    No Known Activations