© 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. 8063
    Prev
    Next
    INDEX
    Explanations

    smoking and tobacco use

    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
     magnets
    -0.12
     hydrogen
    -0.11
     electroly
    -0.11
     Hydro
    -0.11
     Washer
    -0.10
     jelly
    -0.10
     slime
    -0.10
     Hast
    -0.10
     Jelly
    -0.10
     proton
    -0.10
    POSITIVE LOGITS
     smoke
    0.64
     smoking
    0.63
     Smoke
    0.61
     cigarette
    0.61
     smoker
    0.60
     Smoking
    0.59
     smokers
    0.59
     tobacco
    0.59
     smoked
    0.58
     cigarettes
    0.57
    Activations Density 0.408%

    No Known Activations