© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52642
    Prev
    Next
    INDEX
    Explanations

    clauses following 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
    è¿Ļæīįæĺ¯
    -0.10
    éĿ¢çĽ®
    -0.09
     же
    -0.09
    spl
    -0.09
    prise
    -0.09
    æīįåı¯ä»¥
    -0.09
    ä½Ĩæĺ¯æĪij
    -0.08
    æĪij们ä¼ļ
    -0.08
    sume
    -0.08
    ä¼ĹæīĢ
    -0.08
    POSITIVE LOGITS
    ÑĢеÑģ
    0.09
    å¡ij
    0.09
    Licensed
    0.08
    æĺİå¹´
    0.08
    æĦı大
    0.08
     Nationwide
    0.08
     наÑĩал
    0.08
    å°Ĩäºİ
    0.08
    åIJĮåŁİ
    0.08
    uce
    0.08
    Activations Density 0.117%

    No Known Activations