© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49591
    Prev
    Next
    INDEX
    Explanations

    role of X in Y

    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
     Ingredi
    -0.07
    _IMPLEMENT
    -0.07
    пад
    -0.07
    èįĴ
    -0.07
    idt
    -0.07
    åįģä¸īç«ł
    -0.07
    μη
    -0.07
    è´§åĪ°ä»ĺ款
    -0.06
    flags
    -0.06
    æ²ŁéĢļåĴĮ
    -0.06
    POSITIVE LOGITS
    ¯
    0.07
    ovsky
    0.07
    oks
    0.07
     kling
    0.07
    çļĦä¸įèī¯
    0.07
    ulle
    0.07
    period
    0.07
    á»ĵng
    0.07
    èĺĭ
    0.06
    kse
    0.06
    Activations Density 0.085%

    No Known Activations