© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33336
    Prev
    Next
    INDEX
    Explanations

    cigarette smoking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    æĪijçĪ±ä½ł
    -0.09
    活泼
    -0.09
    飫
    -0.09
    æĸĻçIJĨ
    -0.09
    ìĭĿ
    -0.09
    adow
    -0.09
    ESS
    -0.09
    éħįä¸Ĭ
    -0.09
    åĦ¿ç«¥
    -0.08
    ä½İ声
    -0.08
    POSITIVE LOGITS
    åIJ¸çĥŁ
    0.16
    æĬ½çĥŁ
    0.13
     cigarettes
    0.13
    çĥŁ
    0.12
     smoked
    0.12
    åĸĿèĮ¶
    0.11
    çĥŁèįī
    0.11
     smokers
    0.11
     cigaret
    0.11
     smoking
    0.11
    Activations Density 0.148%

    No Known Activations