© 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. 34699
    Prev
    Next
    INDEX
    Explanations

    if code block starts

    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
    ungg
    -0.06
    æ©
    -0.06
    æ³Ľ
    -0.06
     as
    -0.06
    çĶŁ
    -0.06
    æĭī
    -0.06
    é©»
    -0.06
    “
    -0.05
    niec
    -0.05
    για
    -0.05
    POSITIVE LOGITS
    ä»Ĭ度ãģ¯
    0.09
     ìĥģíĻ©ìĿ´
    0.08
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    0.08
    åįİåĽ¾
    0.08
    azin
    0.08
    åı¦å¤ĸä¸Ģ个
    0.08
    jali
    0.08
     Alic
    0.08
    åı¦å¤ĸä¸Ģç§į
    0.08
    ãģ¨ãģĨ
    0.08
    Activations Density 0.066%

    No Known Activations