© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90453
    Prev
    Next
    INDEX
    Explanations

    smoking cessation and behavior

    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
     Cond
    -0.10
     Sweat
    -0.09
     heat
    -0.09
     bunk
    -0.09
    onal
    -0.09
    apon
    -0.09
     cabo
    -0.09
     Steam
    -0.08
     immature
    -0.08
     CNC
    -0.08
    POSITIVE LOGITS
     cigarettes
    0.20
     cigarette
    0.17
     cigaret
    0.16
     Marl
    0.15
     cigars
    0.14
     habit
    0.14
    stress
    0.13
     stress
    0.13
    -cigarettes
    0.13
     relax
    0.13
    Activations Density 0.038%

    No Known Activations