© 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. 14764
    Prev
    Next
    INDEX
    Explanations

    ä¹Łåı¯ä»¥çĶ¨

    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
    æѤåīį
    -0.07
    intang
    -0.06
    ((((
    -0.06
     eslint
    -0.06
    rieve
    -0.06
    缴éĢļ
    -0.06
    赫çĦ¶
    -0.06
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.06
    문íķĻ
    -0.06
    为é¦ĸçļĦ
    -0.06
    POSITIVE LOGITS
    ä¹Łåı¯ä»¥çĶ¨
    0.10
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.09
    ä¹Łåı¯ä»¥åľ¨
    0.08
    举ä¾ĭ
    0.08
    举个ä¾ĭåŃIJ
    0.08
    ouz
    0.08
     Pasc
    0.08
    izz
    0.08
    å¼ķçĶ³
    0.08
    对äºİä¸Ģ个
    0.08
    Activations Density 0.014%

    No Known Activations