© 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. 9075
    Prev
    Next
    INDEX
    Explanations

    understanding information and data

    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
    è°ħ解
    -0.10
    å¿ĥçIJĨåѦ
    -0.09
    人å±ħ
    -0.09
     اÙĦØ°
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    交ä¼ļ
    -0.09
    ç»ĵå®ŀ
    -0.09
    åij¨ä¸Ģ
    -0.08
    ä¸ĢåįĬ
    -0.08
    asted
    -0.08
    POSITIVE LOGITS
    æ¸ħæ¥ļ
    0.11
    ÑĢез
    0.11
    éļıæŶ
    0.10
    æ¢ĵ
    0.09
    èļĢ
    0.09
    ä¸Ģå¼ł
    0.09
    æĥħåĨµ
    0.09
    æķ´ä¸ª
    0.09
     status
    0.09
    çŃīæĥħåĨµ
    0.09
    Activations Density 0.048%

    No Known Activations