© 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. 62855
    Prev
    Next
    INDEX
    Explanations

    ingredients and chemical compounds

    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
    大éĿ¢ç§¯
    -0.09
    缦
    -0.09
    森
    -0.09
    UTES
    -0.09
    åľ¨åŃ¦æł¡
    -0.08
    erval
    -0.08
    åıįè¿ĩæĿ¥
    -0.08
    æĬĵ好
    -0.08
    çļĦä¸Ģ大
    -0.08
    ä¸įåĬ¨
    -0.08
    POSITIVE LOGITS
    éªŀ
    0.09
    宥
    0.09
    åį°è±¡
    0.09
    äºĽè®¸
    0.09
    ahn
    0.08
    å°ijéĩı
    0.08
    oeff
    0.08
    èĩªçĦ¶
    0.08
    opensource
    0.08
    éĢĤæŶ
    0.08
    Activations Density 0.025%

    No Known Activations