© 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. 11796
    Prev
    Next
    INDEX
    Explanations

    textbook editions

    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
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.08
    å½ĵä¸Ģ个
    -0.08
    èĵĦåĬ¿
    -0.07
    认è¯ģåķĨ家
    -0.07
    è®°ä¸ĭ
    -0.07
     primitive
    -0.07
     halt
    -0.07
    å¼ĢåĬ¨
    -0.07
    èĵĦ
    -0.07
    åĩºåĬ¨
    -0.07
    POSITIVE LOGITS
     textbook
    0.08
    ä¸ĩåį·
    0.08
     editions
    0.08
     Everest
    0.07
    èĢħä¹Ł
    0.07
     edition
    0.07
    맥
    0.07
     modular
    0.07
    æ·¼
    0.07
    ç§ijæĬĢèĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.07
    Activations Density 0.084%

    No Known Activations