© 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. 1828
    Prev
    Next
    INDEX
    Explanations

    9/11

    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
    inel
    -0.08
    born
    -0.07
    é¥®é£Łä¸Ĭ
    -0.07
    à§įন
    -0.07
    kaan
    -0.07
    ţe
    -0.07
    ToDevice
    -0.07
    åĻ¨åĴĮ
    -0.07
    ä¸įä¹ı
    -0.07
    edException
    -0.06
    POSITIVE LOGITS
    ï¸İ
    0.10
    ï¸ı
    0.09
    缸è¾ħ缸æĪIJ
    0.08
    ä»ĭçŁ³
    0.07
    俱ä¹IJéĥ¨
    0.07
    ÑĪнÑĭе
    0.07
    西æŀĹ
    0.07
    teo
    0.07
    翼翼
    0.07
    æľĪæľĪ
    0.06
    Activations Density 0.220%

    No Known Activations