© 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. 32504
    Prev
    Next
    INDEX
    Explanations

    transportation routes and infrastructure

    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
    饱满
    -0.06
    çĶŁçIJĨ
    -0.06
    个ä½ĵçļĦ
    -0.06
    æµ·å¸Ĥ
    -0.06
    以身
    -0.06
    æ±łä¸Ń
    -0.06
    åĪ¹éĤ£
    -0.06
    æĬĬæı¡ä½ı
    -0.06
    缼
    -0.06
    æĿ¥èĩªäºİ
    -0.06
    POSITIVE LOGITS
     connecting
    0.12
     routes
    0.12
    æĺ¯ä¸ĢæĿ¡
    0.11
    è¿ŀæİ¥
    0.11
    äºĴèģĶäºĴéĢļ
    0.11
    éĢĻæ¢Ŀ
    0.11
    è¿ĻæĿ¡
    0.11
    connecting
    0.11
    ä¸Ģæ¢Ŀ
    0.11
    è¿ŀæİ¥çļĦ
    0.10
    Activations Density 0.275%

    No Known Activations