© 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. 56561
    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
    åĽ¾æºIJ
    -0.07
    謡
    -0.07
    以ä¸ĭæĺ¯å°ıç¼ĸ
    -0.07
    æŶåĪ»åĪ»
    -0.07
    tolist
    -0.07
    -0.07
    çľĭä½ľæĺ¯
    -0.07
    çİĭä¿Ĭ
    -0.06
    iji
    -0.06
    å·¥ç¨ĭéĻ¢
    -0.06
    POSITIVE LOGITS
    èµŀåIJĮ
    0.07
    åĽŀçŃĶ
    0.07
    ÙĬض
    0.07
    etre
    0.07
     respond
    0.06
    ä¸Ģä½ĵæľº
    0.06
    ربات
    0.06
     пÑĢой
    0.06
    娴
    0.06
    ocked
    0.06
    Activations Density 0.000%

    No Known Activations