© 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. 12021
    Prev
    Next
    INDEX
    Explanations

    also another

    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
    鸳
    -0.06
    ä¸įæ¯Ķ
    -0.06
    ↵
    -0.06
     (
    -0.06
     $
    -0.06
     [
    -0.06
     unless
    -0.06
     th
    -0.06
    /or
    -0.06
    -0.06
    POSITIVE LOGITS
     ebenfalls
    0.14
    ãģĵãģ¡ãĤīãĤĤ
    0.14
    çŃīåħ¶ä»ĸ
    0.13
    another
    0.13
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.12
     likewise
    0.12
    åIJĮæł·æĺ¯
    0.12
    åIJĮæł·
    0.11
    ãģĵãģ¡ãĤīãģ¯
    0.11
    çļĦè¿ĺæľī
    0.11
    Activations Density 0.355%

    No Known Activations