© 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. 24221
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    媲
    -0.08
    illion
    -0.08
    wnd
    -0.08
    denes
    -0.08
    hini
    -0.08
    身ä¸Ĭä¸ĭ
    -0.07
    æĽ´å¤ļ精彩
    -0.07
    htm
    -0.07
    åı¥è¯Ŀ说
    -0.07
    没æľīåħ¶ä»ĸ
    -0.07
    POSITIVE LOGITS
    entan
    0.08
    ãģĦãģł
    0.07
    ãģļãĤĮ
    0.07
    ä¹IJ
    0.06
    æĿ¾
    0.06
    æİ¥
    0.06
     sus
    0.06
    oss
    0.06
    sus
    0.06
    ï¸ı
    0.06
    Activations Density 0.000%

    No Known Activations