© 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. 5293
    Prev
    Next
    INDEX
    Explanations

    quit or quitting 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
    å¿ĥ头
    -0.09
    èļĵ
    -0.08
    çĽ¾
    -0.08
    ajs
    -0.08
    çĶ¸
    -0.08
    èĥ½æ»¡è¶³
    -0.08
    leans
    -0.08
    æİ¥éĢģ
    -0.08
    peror
    -0.08
    serter
    -0.08
    POSITIVE LOGITS
     Moo
    0.08
    ç³Ł
    0.08
    槽
    0.08
    ends
    0.08
    modern
    0.08
     exh
    0.08
    èĻº
    0.08
    endl
    0.08
    ncmp
    0.08
    ç¾
    0.08
    Activations Density 0.012%

    No Known Activations