© 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. 57000
    Prev
    Next
    INDEX
    Explanations

    football defender or back

    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
    ç§ģ
    -0.07
    orio
    -0.07
     Rect
    -0.07
    жде
    -0.07
     rect
    -0.07
    Rect
    -0.06
    _unref
    -0.06
    缼
    -0.06
    ocio
    -0.06
    éļ¾è¿ĩ
    -0.06
    POSITIVE LOGITS
    åħ¼ä»»
    0.11
    åħ¼
    0.11
    ä½įç½®ä¸Ĭ
    0.10
    ä¸ĢèģĮ
    0.10
     겸
    0.09
    æĽ¿è¡¥
    0.08
     kiêm
    0.08
    ispens
    0.08
     interchangeable
    0.08
    æłĩè¯Ĩçłģ
    0.07
    Activations Density 0.113%

    No Known Activations