© 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. 22906
    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
     entire
    -0.08
    ¶
    -0.08
    æĻĸ
    -0.07
    æķ´ä¸ª
    -0.07
     gesamte
    -0.07
    äºĽ
    -0.07
    èĮħ
    -0.07
     Entire
    -0.07
    anan
    -0.07
    欲
    -0.06
    POSITIVE LOGITS
    rok
    0.08
    ä¸ĢçĻ¾å¹´
    0.07
    #
    0.07
    essim
    0.07
     Laure
    0.07
    stable
    0.07
    ¿IJ
    0.07
    ÙİÙĬÙĴ
    0.07
    #index
    0.07
    ord
    0.07
    Activations Density 0.000%

    No Known Activations