© 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. 63973
    Prev
    Next
    INDEX
    Explanations

    Chinese characters or non-English (particularly Asian language) text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    åīįè¿°
    -0.09
    ighth
    -0.08
    æŁIJä¸Ģ
    -0.08
    äºĮèĢħ
    -0.08
    ä¹Łå¹¶éĿŀ
    -0.07
     contempla
    -0.07
     pilo
    -0.07
    糸
    -0.07
    æľ¬å°±æĺ¯
    -0.07
    yleft
    -0.07
    POSITIVE LOGITS
    0.08
    æĿ¥èĩªä¸ŃåĽ½
    0.07
    åľ¨ä¸ŃåĽ½çļĦ
    0.07
    çļĦæľĭåıĭåı¯ä»¥
    0.06
    èĸĦçļĦ
    0.06
    åīµå»º
    0.06
    æĸĮ
    0.06
    çĦ¶åIJİ
    0.06
    管çIJĨæĸ¹éĿ¢
    0.06
    å¬
    0.06
    Activations Density 0.000%

    No Known Activations