© 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. 38110
    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
    Not in Any Lists

    No Comments

    Negative Logits
     напо
    -0.08
    -0.07
    åIJĮä¸Ĭ
    -0.07
    evt
    -0.07
     msgs
    -0.07
    çļĦåĪ¶åº¦
    -0.07
    /XML
    -0.07
    esp
    -0.07
    è¿Ļç§įæĸ¹å¼ı
    -0.07
    è¿ĻäºĽä¸ľè¥¿
    -0.07
    POSITIVE LOGITS
    \:
    0.07
    å·®ä¸į
    0.06
    м
    0.06
    çİ®
    0.06
     Trag
    0.06
    adal
    0.06
     ÙĪÙĩ
    0.06
    /*------------------------------------------------
    0.06
    å®ŀåľ¨æĺ¯
    0.06
    arele
    0.06
    Activations Density 0.000%

    No Known Activations