© 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. 49370
    Prev
    Next
    INDEX
    Explanations

    processing CNC equipment

    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
    人æ°ij为ä¸Ńå¿ĥ
    -0.10
     TikTok
    -0.09
    åŁºå±Ĥæ²»çIJĨ
    -0.09
    麻çĥ¦äºĨ
    -0.09
    çº¾åĽ°
    -0.08
    -0.08
    ç«ĭå¾·æłij人
    -0.08
    åŁİå¸ĤæĽ´æĸ°
    -0.08
    稳å¢ŀéķ¿
    -0.08
     Telegram
    -0.08
    POSITIVE LOGITS
    æĪĸèĢħæĺ¯
    0.10
    æĪĸæĺ¯
    0.10
    çĶļèĩ³æĺ¯
    0.09
    âĢķ
    0.08
    âĢķâĢķ
    0.08
    游离
    0.08
    èĢĮåıĪ
    0.08
    äºĪ
    0.08
    åŃĺåľ¨çĿĢ
    0.07
    ä¸įä½Ĩ
    0.07
    Activations Density 0.012%

    No Known Activations