© 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. 31082
    Prev
    Next
    INDEX
    Explanations

    C# code

    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
    ToShow
    -0.07
    ноÑģÑĤÑĮÑİ
    -0.06
    åIJĥèį¯
    -0.06
    ož
    -0.06
     Mons
    -0.06
    åĬ¨æ¤įçī©
    -0.06
     ám
    -0.06
    FPS
    -0.06
    å°±æĺ¯è¯´
    -0.06
    _human
    -0.06
    POSITIVE LOGITS
    æĸ°ä¸ĸ纪
    0.08
    åĴĮæĹ¥æľ¬
    0.08
    代çłģå¦Ĥä¸ĭ
    0.07
    æ³ģ
    0.07
    /Linux
    0.07
    -style
    0.07
    åĵ¥çļĦ
    0.07
     primitives
    0.07
    åĴĮä¸ŃåĽ½
    0.07
     Selatan
    0.07
    Activations Density 0.337%

    No Known Activations