© 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. 63909
    Prev
    Next
    INDEX
    Explanations

    data types (string, int, object)

    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
    ibaldi
    -0.09
    iette
    -0.08
    	sizeof
    -0.08
    letz
    -0.08
    è¿Ľè¡Įåħ¨éĿ¢
    -0.07
    itten
    -0.07
    abcdefgh
    -0.07
    refix
    -0.07
     niż
    -0.07
    ä»İ严
    -0.07
    POSITIVE LOGITS
    à¸Ńà¸Ļ
    0.07
    ovel
    0.07
    对è¿ĻäºĽ
    0.06
    ä¸Ģç§į
    0.06
    ãĥ¼ãĤ«ãĥ¼
    0.06
    æ¾Ħ
    0.06
    ())[
    0.06
     lagi
    0.05
    解æŀIJ
    0.05
     ↵↵↵
    0.05
    Activations Density 0.032%

    No Known Activations