© 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. 29921
    Prev
    Next
    INDEX
    Explanations

    United States and countries

    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
     Ukra
    -0.07
    hi
    -0.07
     stom
    -0.07
    æĪijèĩªå·±çļĦ
    -0.07
    群ä¼Ĺ路线
    -0.07
    绣æĪĺ
    -0.06
    éĺ³æ°Ķ
    -0.06
    åŃĿå¿ĥ
    -0.06
    ä¸Ģ念
    -0.06
    uh
    -0.06
    POSITIVE LOGITS
    çŃīåĽ½éĻħ
    0.09
    å½ĵåľ°æŶéĹ´
    0.08
    åĮ¹
    0.08
    æŀģåĬĽ
    0.08
    约åIJĪ
    0.08
    é©»åįİ
    0.08
    æĺ¯ç¾İåĽ½
    0.08
    æ¯ķ
    0.08
    å·ŀç«ĭ
    0.08
    çķ¢
    0.07
    Activations Density 0.038%

    No Known Activations