© 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. 26463
    Prev
    Next
    INDEX
    Explanations

    define or explain implementation

    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
    ä¸įå¼Ģ
    -0.08
    æĭĴ
    -0.08
    ä¸įæ¶īåıĬ
    -0.07
    ichern
    -0.07
    åı£çļĦ
    -0.07
    ä¸įåĪĨ
    -0.07
    geschoss
    -0.07
    åħ«é¡¹è§Ħå®ļ
    -0.06
    éĿŀçī©è´¨
    -0.06
     personals
    -0.06
    POSITIVE LOGITS
    æ¯ĶæĪij
    0.12
    代为
    0.09
    æ¯Ķèĩªå·±
    0.09
    æ¯Ķä½ł
    0.09
    æ¯ĶæĪij们
    0.09
    æ¯Ķä»ĸ
    0.08
    æĽ¿ä»ĸ
    0.08
     separately
    0.08
    代è¡Į
    0.08
    åĴĮèĩªå·±
    0.08
    Activations Density 0.197%

    No Known Activations