© 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. 42322
    Prev
    Next
    INDEX
    Explanations

    valid characters or non-alphanumeric

    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
    ä¼ĺç§ĢæķĻå¸Ī
    -0.08
    ä¸ĩå¥Ĺ
    -0.08
    )._
    -0.08
    诽
    -0.08
    ಣ
    -0.08
    空头
    -0.07
    ovac
    -0.07
    æĬĬè¿Ļ个
    -0.07
    Orders
    -0.07
     petró
    -0.07
    POSITIVE LOGITS
     alphanumeric
    0.10
     characters
    0.09
    alnum
    0.09
    åŃĹ符
    0.08
     ajan
    0.07
    _NON
    0.07
     Characters
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    æĹı
    0.07
    adb
    0.07
    Activations Density 0.068%

    No Known Activations