© 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. 15303
    Prev
    Next
    INDEX
    Explanations

    Google search engines

    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
    çīĽè§Ĵ
    -0.08
    æķħéĩĮ
    -0.08
    ä»·æł¼åIJĪçIJĨ
    -0.07
    è§Ĥ念åĴĮ
    -0.07
    åĿļå®ļçIJĨæĥ³ä¿¡å¿µ
    -0.07
    æīĢåľ¨åįķä½į
    -0.07
    -kit
    -0.07
    ISCO
    -0.07
    _Module
    -0.07
    çĶŁåľ¨
    -0.07
    POSITIVE LOGITS
     algorithms
    0.08
    çĪ¬èĻ«
    0.08
    åĪ¶è£ģ
    0.07
     billions
    0.07
    çĪª
    0.07
    /search
    0.07
    å·¨
    0.07
    亿ä¸ĩ
    0.07
    ç®Ĺæ³ķ
    0.07
    crawler
    0.07
    Activations Density 0.148%

    No Known Activations