© 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. 19796
    Prev
    Next
    INDEX
    Explanations

    selectivity

    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
    à¤Łà¤¨à¤¾
    -0.07
    æ·ĭæ¼ĵ
    -0.07
    æĹ¥æ¸¸
    -0.07
    _cached
    -0.07
    ilha
    -0.07
    åĴĮ游æĪı
    -0.07
    zeuge
    -0.06
    èIJ¥åķĨ
    -0.06
    ilater
    -0.06
    ิà¸Ĭ
    -0.06
    POSITIVE LOGITS
    æĢ§çļĦ
    0.11
    ity
    0.10
     ÙĦÙĦغاÙĬØ©
    0.09
    /select
    0.09
    æĢ§æĺ¯
    0.09
    æĢ§åľ°
    0.09
    æĢ§åĴĮ
    0.08
    æĢ§
    0.08
    ivity
    0.08
    åı¯è¨Ģ
    0.08
    Activations Density 0.047%

    No Known Activations