© 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. 58975
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     übrigens
    -0.10
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.09
    对ä¸Ĭè¿°
    -0.08
    بطاÙĦ
    -0.08
    ÑĥÑĢÑģ
    -0.08
    订éĺħä¸ĵæłı
    -0.08
    è¿Ŀåıįä¸Ĭè¿°
    -0.08
     ÐijоÑĢи
    -0.07
     Horiz
    -0.07
    моно
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.09
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.08
    ↵
    0.06
    \n
    0.05
    0.05
    æľĢæĸ°åıijå¸ĥ
    0.05
    âĢIJ
    0.05
     ...
    0.05
    ...
    0.05
    ãģĿãĤĮãģ«
    0.05
    Activations Density 0.000%

    No Known Activations