© 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. 41923
    Prev
    Next
    INDEX
    Explanations

    **H** followed by **\*\***

    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
    éļ
    -0.08
     wart
    -0.07
    ault
    -0.07
     ëģ¼
    -0.07
    æľªæĪIJå¹´
    -0.06
    é²ľå«©
    -0.06
    å¹´åįİ
    -0.06
    çļĦéĩį大
    -0.06
    跨度
    -0.06
    éĩį大çļĦ
    -0.06
    POSITIVE LOGITS
     Reit
    0.08
    CRET
    0.08
    æ¥Ķ
    0.08
     sovra
    0.07
    ä¸Ńä»ĭæľįåĬ¡
    0.07
    æ¥ŀ
    0.07
    宾
    0.07
    æĸ°ä¹¦
    0.07
    ackle
    0.07
    ogne
    0.06
    Activations Density 0.003%

    No Known Activations