© 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. 3499
    Prev
    Next
    INDEX
    Explanations

    layout and programming keywords

    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
    lines
    -0.07
    -addon
    -0.07
    åĪ°èĢģ
    -0.06
    Õ®
    -0.06
    ದà³ģ
    -0.06
    ê°ķ
    -0.06
    ighb
    -0.06
     olds
    -0.06
    -dom
    -0.06
    æĿ¥äºº
    -0.06
    POSITIVE LOGITS
    ä¸ŃçļĦä¸Ģ个
    0.08
    çļĦä¸Ģéĥ¨åĪĨ
    0.08
    é¦ĸä½į
    0.08
    çļĦ大éĥ¨åĪĨ
    0.08
    é¦ĸ
    0.08
    ä¸ŃæľĢ
    0.08
    æŁIJä¸Ģ
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    ãģĨãģ¡ãģ®
    0.08
    çļĦé¦ĸ
    0.08
    Activations Density 0.069%

    No Known Activations