© 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. 9384
    Prev
    Next
    INDEX
    Explanations

    "-ed words"

    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
    é³ĸ
    -0.09
    主ä¹īèĢħ
    -0.09
    æĻºåķĨ
    -0.09
    é«ĺåħ´
    -0.09
    èı½
    -0.08
    ç³Ĺ
    -0.08
    åħ¨åªĴä½ĵ
    -0.08
    æ¹İ
    -0.08
    çıª
    -0.08
    rup
    -0.08
    POSITIVE LOGITS
    ypi
    0.10
    涯
    0.09
    带æĿ¥çļĦ
    0.09
    带ç»Ļ
    0.09
    路段
    0.09
     اÙĦعÙħ
    0.09
    èľļ
    0.08
    åĮºåŁŁ
    0.08
    æĹ¥åŃIJ
    0.08
    å¢Ģ
    0.08
    Activations Density 0.571%

    No Known Activations