© 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. 48639
    Prev
    Next
    INDEX
    Explanations

    Crosstab, Hua, Anatoly, dengue, Corona, Hajdúdorog, Yam, Garrison

    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
    æĢ»èĢĮè¨Ģä¹ĭ
    -0.09
    ä¸Ģ举
    -0.09
    æĢĻ
    -0.09
    volution
    -0.08
    è¯ŀ
    -0.08
    è±¢
    -0.08
    æĿ¥åĪ°äºĨ
    -0.08
    åķ¡
    -0.08
     Tomas
    -0.08
    èĤĩ
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    eration
    0.09
    好å¤ļ
    0.09
    èĭ¥æĺ¯
    0.09
    wards
    0.09
    mani
    0.09
    ج
    0.09
    gré
    0.09
     ern
    0.08
    ê¶Į
    0.08
    Activations Density 1.287%

    No Known Activations