© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37342
    Prev
    Next
    INDEX
    Explanations

    director of

    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
    èĬ¥
    -0.10
    ãģĿ
    -0.09
    å¼Ģåħĥ
    -0.09
    æĪ¿ä¸ľ
    -0.09
    æİĴåIJį第ä¸Ģ
    -0.08
    çŁ³æ²¹åĮĸå·¥
    -0.08
     pimp
    -0.08
    çħľ
    -0.08
    梳
    -0.08
    é¢Ĩè¢ĸ
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥æ´»åĬ¨
    0.10
    æ§İ
    0.10
    çľĭå¾Ĺ
    0.09
    ette
    0.09
    IPA
    0.09
    éĴ³
    0.08
     ÐijеÑģ
    0.08
    åĵ¡
    0.08
     gar
    0.08
    rema
    0.08
    Activations Density 0.014%

    No Known Activations