© 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. 41051
    Prev
    Next
    INDEX
    Explanations

    internal standard

    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
    åľ¨åįĹ
    -0.07
    hier
    -0.07
     fastest
    -0.07
    åIJĬéĶĢ
    -0.07
     resid
    -0.07
    Ø´ÙĨ
    -0.07
    inject
    -0.07
    ä¸įçŁ¥
    -0.07
     Cos
    -0.06
    Relations
    -0.06
    POSITIVE LOGITS
     boundary
    0.08
    éĩijæĸ¯
    0.08
    boundary
    0.07
    çķĮéĻIJ
    0.07
    è¨
    0.07
    èĮ
    0.07
    é¸¡æ¯Ľ
    0.07
    istical
    0.07
     Yates
    0.07
    alz
    0.07
    Activations Density 0.001%

    No Known Activations