© 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. 42410
    Prev
    Next
    INDEX
    Explanations

    purposes

    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
    对äºİè¿ĻäºĽ
    -0.11
    对äºİ
    -0.09
    对äºİè¿Ļ个
    -0.09
    ãĤĴ使çĶ¨ãģĹãģ¦
    -0.08
    对äºİä¸Ģ个
    -0.08
    æĶ¯ä»ĺæĸ¹å¼ı
    -0.08
    åºĶçĶ¨æĬĢæľ¯
    -0.07
    lineno
    -0.07
    æݧåĪ¶æĬĢæľ¯
    -0.07
     ÙĪسÙĦ
    -0.07
    POSITIVE LOGITS
     purposes
    0.23
     sake
    0.21
     Zwecke
    0.19
     ÙĪÙĦÙĦ
    0.14
    缮çļĦçļĦ
    0.12
    èµ·è§ģ
    0.12
     keperluan
    0.11
     ÑĨелей
    0.10
    å°ĨæĿ¥çļĦ
    0.10
    ä¹ĭçĶ¨
    0.10
    Activations Density 0.555%

    No Known Activations