© 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. 48326
    Prev
    Next
    INDEX
    Explanations

    followed by punctuation or equation

    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
    ç»ĻæĪijçļĦ
    -0.08
    æ°¸è¿ľçļĦ
    -0.07
    éĤ£ç§į
    -0.07
    çļĦéĤ£ä¸ª
    -0.07
    æīĢ以çİ°åľ¨
    -0.07
    寮
    -0.07
    ç»ĻæĪij们çļĦ
    -0.07
    åı¦å¤ĸä¸Ģ个
    -0.07
    æĪ·æĪ·
    -0.07
    eszt
    -0.07
    POSITIVE LOGITS
    æľī以ä¸ĭ
    0.08
    ollow
    0.08
    ä¸Ĭè¿°
    0.07
    話ãģ¯
    0.07
    поÑĢ
    0.07
    owed
    0.07
    以ä¸ĭæĿ¡ä»¶
    0.07
    ernet
    0.07
    ATTER
    0.07
    æīĭå¿Ļ
    0.07
    Activations Density 0.017%

    No Known Activations