© 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. 42146
    Prev
    Next
    INDEX
    Explanations

    contractual agreements

    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
    elok
    -0.07
    æ¯ıéĢ¢
    -0.07
     Wonder
    -0.06
    alion
    -0.06
    Wonder
    -0.06
    è¯Ńè¨Ģ表达
    -0.06
    ÙĪاÙĦÙĬ
    -0.06
    åºŃ
    -0.06
    ×IJר
    -0.06
    è¿ĩçļĦ
    -0.06
    POSITIVE LOGITS
    æĸ°çļĦ
    0.17
    æ¯Ķ以åīį
    0.17
    æ¯Ķ以å¾Ģ
    0.15
    çļĦåħ¨æĸ°
    0.15
    çŃīæĸ°
    0.14
     new
    0.14
    æĸ°ãģŁãģª
    0.14
    æĸ°ãģĹãģĦ
    0.13
    ä¸Ģ个æĸ°çļĦ
    0.13
     новой
    0.13
    Activations Density 0.327%

    No Known Activations