© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 548
    Prev
    Next
    INDEX
    Explanations

    literary movement or art school

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    饼
    -0.07
    ä¹łæĥ¯æĢ§
    -0.07
    累计
    -0.07
    æģĴ
    -0.07
    常è§ĦçļĦ
    -0.07
     Majesty
    -0.06
    常年
    -0.06
    åĨĹ
    -0.06
    åįĥçĻ¾
    -0.06
    åįĥåı¤
    -0.06
    POSITIVE LOGITS
    å½ĵæŶ
    0.11
    é¼İ缼
    0.10
    åľ¨å½ĵæŶ
    0.10
    纲é¢Ĩ
    0.10
    çķ¶æĻĤ
    0.09
    ãĤ°ãĥ«ãĥ¼ãĥĹ
    0.09
    西海岸
    0.09
     그룹
    0.09
    æķĻäºİ
    0.09
    è¿Ļ群
    0.09
    Activations Density 0.084%

    No Known Activations