© 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. 9477
    Prev
    Next
    INDEX
    Explanations

    Chinese punctuation

    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
    为æĤ¨
    -0.10
    æĸ¹éĿ¢çļĦ
    -0.09
    驶
    -0.08
    æīĢè°ĵçļĦ
    -0.08
    为æĤ¨æıIJä¾Ľ
    -0.08
    黯
    -0.08
     yan
    -0.08
    èĬ±äºĨ
    -0.08
     Continuing
    -0.08
    为æĪij们
    -0.08
    POSITIVE LOGITS
    å®ĥæĺ¯
    0.15
    è¿Ļä¹Łæĺ¯
    0.13
    å®ĥ
    0.13
    ä½Ĩ
    0.11
    ä½Ĩä»İ
    0.10
     it
    0.10
    ä½Ĩåľ¨
    0.10
    odef
    0.09
    è¿Ļå°±æĺ¯
    0.09
    è¿ĻéĩĮ
    0.09
    Activations Density 0.291%

    No Known Activations