© 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. 22854
    Prev
    Next
    INDEX
    Explanations

    programming code syntax

    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
    ofil
    -0.07
    icato
    -0.07
    ä¼ģä¸ļæıIJä¾Ľ
    -0.07
    uesa
    -0.07
    ä»Ĺ
    -0.07
    /rest
    -0.07
    zeg
    -0.07
    欢声
    -0.07
     ['/
    -0.07
    æıIJä¾ĽæĽ´å¤ļçļĦ
    -0.07
    POSITIVE LOGITS
    éĴ°
    0.08
    è´
    0.07
    odesk
    0.07
    é·
    0.06
    ä¸ĢåIJ¬
    0.06
    åIJ¬åIJ¬
    0.06
    OTES
    0.06
    locale
    0.06
    ç»ĵæŀĦä¸Ń
    0.06
    åįĵ
    0.06
    Activations Density 0.002%

    No Known Activations