© 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. 55606
    Prev
    Next
    INDEX
    Explanations

    Korean or Korea

    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
    æĶĢæŀĿèĬ±
    -0.09
    gypt
    -0.09
    æĦı大åĪ©
    -0.08
     ì¤Ħ
    -0.07
    大éĿ©åij½
    -0.07
     иÑĤалÑĮÑı
    -0.07
     Pubbl
    -0.07
     Podesta
    -0.07
    泸
    -0.07
     Italian
    -0.07
    POSITIVE LOGITS
    æľĿé²ľ
    0.14
     Seoul
    0.14
    飩è¯Ń
    0.13
     Korean
    0.13
    éŁ©åĽ½
    0.13
    é¦ĸå°Ķ
    0.13
     Pyongyang
    0.12
     Samsung
    0.12
     Koreans
    0.12
     Korea
    0.12
    Activations Density 0.385%

    No Known Activations