© 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. 12054
    Prev
    Next
    INDEX
    Explanations

    album, band, region, episode

    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
    NullOr
    -0.06
    idian
    -0.06
    vh
    -0.06
    .cb
    -0.06
    æĥħåĨµçļĦ
    -0.06
    缸åħ³æ³ķå¾ĭæ³ķè§Ħ
    -0.06
    æĿ¡ä»¶ä¸ĭçļĦ
    -0.06
    æĥħåĨµåıĬ
    -0.06
    使åĩº
    -0.06
    ел
    -0.05
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.11
    éĺ¿æĭī伯
    0.10
    åĬłæĭ¿å¤§
    0.10
    俱ä¹IJéĥ¨
    0.08
     اجرا
    0.08
    ä»»ä½ķä¸ľè¥¿
    0.07
    人说
    0.07
    åIJĦç§įåIJĦæł·
    0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    aksa
    0.07
    Activations Density 0.022%

    No Known Activations