© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56861
    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
    égor
    -0.07
     enumerated
    -0.07
     enumer
    -0.07
     bila
    -0.06
     enumerate
    -0.06
    åĪĿ
    -0.06
     enumeration
    -0.06
    亦åı¯
    -0.06
     unanim
    -0.06
     mè
    -0.06
    POSITIVE LOGITS
    æīĵçĿĢ
    0.08
    XXX
    0.08
    è¿ĺæĺ¯åı¯ä»¥
    0.08
    \\\\
    0.08
    paque
    0.08
    è¿ĺæĺ¯éľĢè¦ģ
    0.08
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.08
    pera
    0.08
    è¿Ļä¹Ī大çļĦ
    0.08
    åıĭæĥħæıIJ示
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.