© 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. 13100
    Prev
    Next
    INDEX
    Explanations

    code block punctuation and keywords

    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
     Cafe
    -0.07
    çĤ¹åĩ»ä¸Ĭæĸ¹
    -0.07
    æĢ§çļĦ
    -0.07
    å¼ĤæĢ§
    -0.07
    æĹłå½±
    -0.07
    Ú¯ÛĮ
    -0.07
    å¨Ĩ
    -0.06
    ulk
    -0.06
    изи
    -0.06
    åѦä¼ļ
    -0.06
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.09
    缸è¾ħ缸æĪIJ
    0.09
    è¿Ļæĺ¯æĪij们
    0.08
    俱ä¹IJéĥ¨
    0.08
    åĬłæĭ¿å¤§
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
     dunque
    0.08
    ondre
    0.07
    éĺ¿æĭī伯
    0.07
     tedy
    0.07
    Activations Density 0.002%

    No Known Activations