© 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. 20090
    Prev
    Next
    INDEX
    Explanations

    statistical data and figures

    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
    第ä¸Ģ课
    -0.08
    ilon
    -0.07
    .constructor
    -0.07
    kuš
    -0.07
     cloned
    -0.07
    etag
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.07
    ä¼ģä¸ļæĸĩåĮĸ
    -0.07
    åĩºèµĦæ¯Ķä¾ĭ
    -0.07
    åĢĻè£ľ
    -0.07
    POSITIVE LOGITS
     data
    0.14
     disag
    0.13
    è¿ĻäºĽæķ°æį®
    0.12
    æķ°æį®
    0.12
    æķ°æį®è¿Ľè¡Į
    0.11
    æķ°æį®çļĦ
    0.11
    data
    0.11
    çļĦæķ°æį®
    0.11
     Data
    0.11
     annual
    0.10
    Activations Density 0.482%

    No Known Activations