© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3403
    Prev
    Next
    INDEX
    Explanations

    torque pulsation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä»»åĬ³ä»»æĢ¨
    -0.07
    drv
    -0.07
    .sections
    -0.07
    éĹ®åĮ»çĶŁ
    -0.07
    adb
    -0.06
    å¹²äºĭåĪĽä¸ļ
    -0.06
    æĥ©æ²»
    -0.06
     Tough
    -0.06
     psz
    -0.06
    \Database
    -0.06
    POSITIVE LOGITS
    è¿ĩ度
    0.08
    è´ª
    0.08
     insufficient
    0.08
    ä½ĨåIJĮæŶ
    0.08
    ä¸įä¸ĭæĿ¥
    0.08
    èݱæĸ¯
    0.08
    ublin
    0.08
    ä¸įå¦Ĥ
    0.08
    太好
    0.08
    åıĤå·®ä¸įé½IJ
    0.07
    Activations Density 0.621%

    No Known Activations