© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16170
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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
    æģŃ
    -0.07
    ÙĨب
    -0.07
    èĸª
    -0.06
    èĬĿ
    -0.06
    çıĬ
    -0.06
     tér
    -0.06
    imit
    -0.06
    å½±
    -0.06
     correspond
    -0.06
    .splitext
    -0.06
    POSITIVE LOGITS
    ctions
    0.08
    访éĹ®éĩı
    0.08
    åĨħ容æıIJä¾Ľæĸ¹
    0.07
    à¤Ĺà¥Ģ
    0.07
    æī«çłģåħ³æ³¨
    0.07
    ocode
    0.07
    ioen
    0.07
    é£ĵ
    0.07
    æĺ¯ä¸ĸçķĮä¸Ĭ
    0.07
    æī¬åŃIJ
    0.07
    Activations Density 0.002%

    No Known Activations