© 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. 62110
    Prev
    Next
    INDEX
    Explanations

    alcohol consumption

    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
    burst
    -0.09
    ç¦ħ
    -0.09
    FromNib
    -0.09
     undermin
    -0.09
     METH
    -0.09
     unf
    -0.08
     refl
    -0.08
    éĢ¼
    -0.08
    odont
    -0.08
    沩
    -0.08
    POSITIVE LOGITS
    ç¨Ķ
    0.10
    æĪĸå¤ļ
    0.09
     Lager
    0.09
    èıĢ
    0.09
    èĭ¡
    0.08
    ç°Į
    0.08
    æ´İ
    0.08
    æ»ŀåIJİ
    0.08
    æĦŁæĥħ
    0.08
    Things
    0.08
    Activations Density 0.033%

    No Known Activations