© 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. 61551
    Prev
    Next
    INDEX
    Explanations

    Chinese provinces and dynasties

    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
    ä½³èĬĤ
    -0.07
    åĸ·
    -0.07
    ä»ķ
    -0.06
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.06
    åĨĪ
    -0.06
    æĤ¬
    -0.06
    å¿įèĢħ
    -0.06
    éĵ¿
    -0.06
     sverige
    -0.06
    ATH
    -0.06
    POSITIVE LOGITS
     yuan
    0.13
     Qing
    0.13
     Yuan
    0.12
     Jiang
    0.12
     Zh
    0.12
     Guangdong
    0.12
     Guang
    0.12
     Zhang
    0.12
     Zhu
    0.12
     Tian
    0.11
    Activations Density 1.283%

    No Known Activations