© 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. 17241
    Prev
    Next
    INDEX
    Explanations

    measure theory

    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
    áŀī
    -0.09
    rung
    -0.09
    å±±ä¸Ĭ
    -0.08
    ansi
    -0.08
    ä¸įå±Ī
    -0.07
    主åŁİ
    -0.07
    MainThread
    -0.07
    arend
    -0.07
    ä¸ĢçĤ¹åĦ¿
    -0.07
    AndGet
    -0.07
    POSITIVE LOGITS
    æĢ»éĿ¢ç§¯
    0.09
     density
    0.08
    éĿ¢ç§¯
    0.08
    çļĦéĿ¢ç§¯
    0.08
    density
    0.08
    -density
    0.07
    åįłåħ¬åı¸
    0.07
    éĿ¢ç§¯ä¸º
    0.07
     area
    0.07
    åŃļ
    0.07
    Activations Density 0.005%

    No Known Activations