© 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. 62362
    Prev
    Next
    INDEX
    Explanations

    æľ¥è¡Į/æľ¥è¯´ (transmission/reporting)

    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åĪ°
    -0.09
    大家对
    -0.08
    æ¶Īè´¹èĢħ对
    -0.08
    人们对
    -0.08
    人被
    -0.07
    åĬĽãģ¯
    -0.07
    çĶ¨æĪ·å¯¹
    -0.07
    æĿ¡ä»¶æĺ¯
    -0.07
    æŃ£åĢ¼
    -0.07
    ؤÙĩ
    -0.07
    POSITIVE LOGITS
    羣å®ŀæĢ§è´Łè´£
    0.15
    åĨħå®¹è¿Ľè¡Į
    0.15
    ä¿¡æģ¯è¿Ľè¡Į
    0.14
    çļĦ人æĿ¥è¯´
    0.14
    èĢĮè¨Ģ
    0.14
    æĥħåĨµè¿Ľè¡Į
    0.13
    éĹ®é¢ĺè¿Ľè¡Į
    0.13
    æĿ¥è¯´
    0.13
    æĿ¥è¯´æĺ¯
    0.13
    æķ°æį®è¿Ľè¡Į
    0.13
    Activations Density 0.009%

    No Known Activations