© 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. 26360
    Prev
    Next
    INDEX
    Explanations

    away from

    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
    è¿ĻçĤ¹
    -0.08
    æľī两ç§į
    -0.08
    两ç§įæĸ¹å¼ı
    -0.07
    ëħIJ
    -0.07
    æѤäºĭ
    -0.07
    主è¦ģ表çİ°åľ¨
    -0.07
    æľīä¸īç§į
    -0.07
    kena
    -0.07
    rence
    -0.07
    è¿Ļé¡¹å·¥ä½ľ
    -0.07
    POSITIVE LOGITS
    è¿ĻäºĽä¸ľè¥¿
    0.14
    è¿ĻäºĽéĥ½æĺ¯
    0.12
    è¿ĻäºĽ
    0.12
    åĽłä¸ºè¿ĻäºĽ
    0.11
    ãģ©ãĤĮãĤĤ
    0.11
    å°Ĩè¿ĻäºĽ
    0.11
    ä½Ĩè¿ĻäºĽ
    0.11
    èĢĮè¿ĻäºĽ
    0.11
    éĢļè¿ĩè¿ĻäºĽ
    0.11
    éĢĻäºĽ
    0.11
    Activations Density 0.423%

    No Known Activations