© 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. 63868
    Prev
    Next
    INDEX
    Explanations

    IR Group, 2PM, R-124, N-in

    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
    æĸ¹æ³ķæĿ¥
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    çļĦèĩªå·±
    -0.08
    æĿ¥è¯´æĺ¯
    -0.08
    ä»įèĥ½
    -0.08
    以ä¸ĭæĿ¡ä»¶
    -0.07
    imbledon
    -0.07
    ä¼ļåıijçİ°
    -0.07
    ä½łä¼ļåıijçİ°
    -0.07
    å°±ä¼ļåıijçİ°
    -0.07
    POSITIVE LOGITS
    æĺ¯æĪijåĽ½
    0.10
    ä½ľä¸ºä¸Ģç§į
    0.09
    æĺ¯æĮĩ
    0.09
    æ³ķæĺ¯
    0.09
    æľ¬æĺ¯
    0.09
    æĺ¯ä¸ŃåĽ½
    0.08
    æĺ¯äººç±»
    0.08
    æĢ§æĺ¯
    0.08
    ãģ¨ãģĦãģĪãģ°
    0.08
    æĺ¯ä¸Ģç§į
    0.08
    Activations Density 0.022%

    No Known Activations