© 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. 39680
    Prev
    Next
    INDEX
    Explanations

    small, large, huge

    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
    ç§°ä½ľ
    -0.08
    éķ¿è¾¾
    -0.07
    æŶéķ¿
    -0.07
    бло
    -0.07
    ãģĻãĤĬ
    -0.07
    诧
    -0.07
    åľ°éĿ¢çļĦ
    -0.07
     lÃłn
    -0.07
    æľŁéĻIJ为
    -0.07
    argas
    -0.07
    POSITIVE LOGITS
     enough
    0.15
     Enough
    0.11
     genug
    0.11
     relative
    0.11
    çĽ¸å¯¹äºİ
    0.10
    ìĪĺë¡Ŀ
    0.10
    Enough
    0.10
     جداÙĭ
    0.09
     جدÙĭا
    0.09
    relative
    0.09
    Activations Density 0.034%

    No Known Activations