© 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. 18588
    Prev
    Next
    INDEX
    Explanations

    protect property and prevent damage

    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
     supplementary
    -0.08
     اÙĦÙĥÙĬÙħÙĬا
    -0.08
    æĹłå¾®ä¸įèĩ³
    -0.07
    ellini
    -0.07
    ÅĻen
    -0.07
     Bowman
    -0.07
    常ä½ı人åı£
    -0.07
    ocab
    -0.07
    ienti
    -0.07
    ä¸įåı¯ç¼ºå°ij
    -0.07
    POSITIVE LOGITS
    åıĬ对
    0.08
    æī°
    0.08
    åIJĮæĹ¶ä¹Ł
    0.07
    并使
    0.07
    è¿Ļä¸įä»ħ
    0.07
    ä¹Łæĺ¯å¯¹
    0.07
    æĹ¢æĺ¯
    0.07
    åıĬ个人
    0.07
    ìĿ´ìŀIJ
    0.07
    otty
    0.07
    Activations Density 0.359%

    No Known Activations