© 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. 37464
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    å¦ĤåIJĮä¸Ģ
    -0.09
    å¦ĤåĪĿ
    -0.08
    å¦ĤåIJĮ
    -0.08
    ä½ľä¸ºä¸Ģ项
    -0.07
    çĬ¹å¦Ĥ
    -0.07
    çķľ
    -0.07
    æĪĸèĢħ说
    -0.07
    ãģ¨ãģĦãģĨæĦıåij³
    -0.07
    itÃł
    -0.07
     somehow
    -0.07
    POSITIVE LOGITS
    ä¹ĭç±»
    0.07
    ãģªãģ©ãģ¯
    0.07
    çŃīçļĦ
    0.07
     etc
    0.07
     czy
    0.07
     others
    0.07
    çŃīåľ¨
    0.07
    ÃįC
    0.07
    /etc
    0.07
    èĬ¹
    0.07
    Activations Density 0.350%

    No Known Activations