© 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. 47706
    Prev
    Next
    INDEX
    Explanations

    Greek letters and math symbols

    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
     bumps
    -0.06
    çľ¼çļĦ
    -0.06
    æİĴéĻ¤
    -0.06
    ä¾µæĿĥ责任
    -0.06
    åį¡çļĦ
    -0.06
    æļ´éľ²åľ¨
    -0.06
    认é¢Ĩ
    -0.06
    ил
    -0.05
    tim
    -0.05
    åĬ¨çĶ»çīĩ
    -0.05
    POSITIVE LOGITS
    _gender
    0.08
    ignes
    0.08
    妮
    0.07
     DECR
    0.07
    âĢ¦]
    0.07
    /topics
    0.07
    ä¼ģä¸ļæıIJä¾Ľ
    0.07
    gender
    0.07
     ÑģпÑĢе
    0.07
     '%"
    0.07
    Activations Density 0.018%

    No Known Activations