© 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. 13954
    Prev
    Next
    INDEX
    Explanations

    salad ingredients

    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
     brew
    -0.12
     Milk
    -0.12
     dist
    -0.12
     baker
    -0.12
    Beer
    -0.11
     Rhe
    -0.11
     furnace
    -0.11
     beer
    -0.11
     whiskey
    -0.11
     Brew
    -0.11
    POSITIVE LOGITS
     salad
    0.39
     Salad
    0.34
     salads
    0.33
     dressing
    0.32
     lettuce
    0.27
     Dress
    0.24
     dress
    0.21
     greens
    0.20
    Sal
    0.18
     Caesar
    0.18
    Activations Density 0.215%

    No Known Activations