© 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. 1769
    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
    åĪĿè§ģ
    -0.08
    çĶ»æ³ķ
    -0.08
    -know
    -0.08
    å¤įæĿĤçļĦ
    -0.07
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    -0.07
    stu
    -0.07
    oldt
    -0.07
    潺
    -0.07
    çĶ»çļĦ
    -0.07
    缶
    -0.07
    POSITIVE LOGITS
    ç»ĵ论
    0.07
     concludes
    0.07
    Conclusion
    0.07
     vare
    0.07
    iglich
    0.06
     conclusion
    0.06
     conclude
    0.06
     concluded
    0.06
    åı¦ä¸ĢåįĬ
    0.06
    ï¸İ
    0.06
    Activations Density 0.000%

    No Known Activations