© 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. 51466
    Prev
    Next
    INDEX
    Explanations

    female titles and roles

    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
    巴士
    -0.09
    缴åįĩ
    -0.08
    è´¯éĢļ
    -0.08
    è°ĥåĬ¨
    -0.08
    çļĦ积æŀģæĢ§
    -0.08
    伸
    -0.07
    æľĢåIJİä¸Ģ次
    -0.07
    holding
    -0.07
    æŶéĻIJ
    -0.07
    _IW
    -0.07
    POSITIVE LOGITS
    -sama
    0.11
    æĮĩ令
    0.11
     ÑħозÑı
    0.11
    åIJĿ
    0.11
    é«ĺåħ´
    0.09
    大佬
    0.09
    æ´ŀå¯Ł
    0.09
    ãģķãģ¾
    0.09
    泡泡
    0.09
    é¢Ĩ导ä¸ĭ
    0.09
    Activations Density 0.187%

    No Known Activations