© 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. 4223
    Prev
    Next
    INDEX
    Explanations

    department names or acronyms

    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
    æĬĺ
    -0.08
    åİ¿å§Ķ书记
    -0.08
    åħ¬åı¸ç«łç¨ĭ
    -0.08
    ذا
    -0.08
    ä¼ļè®®åı¬å¼Ģ
    -0.07
    åĨį好
    -0.07
    åݿ人æ°ijæ³ķéĻ¢
    -0.07
     Maranh
    -0.07
    å¾·éŁ³
    -0.07
    ÃģP
    -0.07
    POSITIVE LOGITS
     ausp
    0.09
    æī§
    0.09
    -funded
    0.08
    æĹĹä¸ĭ
    0.08
    æĹĹä¸ĭçļĦ
    0.08
    -owned
    0.08
    ä¸ĭå±ŀ
    0.07
    ighthouse
    0.07
    缴å±ŀ
    0.07
     ÙħÙħ
    0.07
    Activations Density 0.676%

    No Known Activations