© 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. 27064
    Prev
    Next
    INDEX
    Explanations

    indicated herein

    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
    åĽłä¸ºå®ĥ
    -0.10
    åĽłä¸ºæĪij们
    -0.10
    åĽłä¸ºä»ĸ
    -0.09
    æĺ¯ä»ĸ
    -0.09
    æĢ§åĴĮ
    -0.09
    åĽłä¸ºæĪij
    -0.09
    对æĪij们
    -0.08
    çļĦæĸ¹å¼ıæĿ¥
    -0.08
    ãĤĪãģĨãģ§
    -0.08
    åĽłä¸º
    -0.08
    POSITIVE LOGITS
    æĪijä»¬ä¹Ł
    0.12
    æĪijä¼ļ
    0.11
    æĪij们ä¼ļ
    0.11
    ä½łä¼ļ
    0.11
    ,
    0.11
     ÙģØ¥ÙĨ
    0.11
    大家åı¯ä»¥
    0.11
    æĪij们åı¯ä»¥
    0.11
    æĪij们éĥ½
    0.11
    ä½łåı¯ä»¥
    0.10
    Activations Density 0.717%

    No Known Activations