© 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. 64659
    Prev
    Next
    INDEX
    Explanations

    const abbreviations likeMIC, pert, main

    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
     berdua
    -0.08
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.08
    обо
    -0.07
    umm
    -0.07
     Ðŀба
    -0.07
    bara
    -0.07
    ãģ©ãģ¡ãĤī
    -0.07
    ersen
    -0.07
    äºĮèĢħ
    -0.06
    ooth
    -0.06
    POSITIVE LOGITS
    çļĦåIJĦ个
    0.14
    çļĦåIJĦ项
    0.13
     various
    0.13
    åIJĦ项
    0.12
     Various
    0.12
    åIJĦéłħ
    0.11
    çļĦåIJĦç§į
    0.11
    ä¸Ģç³»åĪĹ
    0.11
    æĺ¥å¤ıç§ĭåĨ¬
    0.11
    çļĦä¸Ģç³»åĪĹ
    0.11
    Activations Density 1.161%

    No Known Activations