© 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. 30269
    Prev
    Next
    INDEX
    Explanations

    korean words and characters

    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
    :nil
    -0.07
     rasp
    -0.07
    Nil
    -0.06
     Www
    -0.06
    quel
    -0.06
     ìĽ¹ìĤ¬ìĿ´íĬ¸ê°Ģ
    -0.06
     Trì
    -0.06
     Rü
    -0.06
    åºĵ
    -0.06
    ytics
    -0.06
    POSITIVE LOGITS
     Korea
    0.12
    yeong
    0.11
    飩åī§
    0.10
     Koreans
    0.10
     Korean
    0.10
     Seoul
    0.10
    åľ¨éŁ©åĽ½
    0.10
    飩è¯Ń
    0.10
    éŁ©åĽ½
    0.09
    飩å¼ı
    0.09
    Activations Density 0.232%

    No Known Activations