© 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. 49159
    Prev
    Next
    INDEX
    Explanations

    query to, uboot, calls, History API, vitro, pointer

    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
    ä¹ĭçĶ¨
    -0.08
    使çĶ¨çļĦæĺ¯
    -0.08
    éĩĩçĶ¨çļĦæĺ¯
    -0.08
    Ãłnh
    -0.08
    请使çĶ¨
    -0.08
    使çĶ¨éģĵåħ·
    -0.07
    使çĶ¨èµ·æĿ¥
    -0.07
    æĬĢæľ¯åºĶçĶ¨
    -0.07
     usados
    -0.07
     using
    -0.07
    POSITIVE LOGITS
    çļĦæĸ¹å¼ıæĿ¥
    0.16
    çļĦæĸ¹æ³ķæĿ¥
    0.16
    æŶéĹ´æĿ¥
    0.15
    æĸ¹æ³ķæĿ¥
    0.14
     instead
    0.14
    çļĦæĸ¹å¼ıè¿Ľè¡Į
    0.13
    æķ°æį®è¿Ľè¡Į
    0.13
    instead
    0.13
    æĸ¹å¼ıæĿ¥
    0.13
    èĢĮä¸įæĺ¯
    0.13
    Activations Density 0.918%

    No Known Activations