© 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. 46641
    Prev
    Next
    INDEX
    Explanations

    design, configuration, code, database

    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
    太éĥİ
    -0.08
    /auto
    -0.07
    çŁ¥ä¹ĭ
    -0.07
    综åIJĪæĶ¹éĿ©
    -0.07
     Brent
    -0.07
     Tamb
    -0.07
    å¼łåĺ´
    -0.07
    (/[
    -0.06
    amba
    -0.06
    绥
    -0.06
    POSITIVE LOGITS
    æīĴ
    0.06
    egot
    0.06
    åĴĮç»Ħç»ĩ
    0.06
    wez
    0.06
    leton
    0.06
    举éģĵ
    0.06
     hom
    0.06
    ämpft
    0.06
    èĥľ
    0.06
    arth
    0.06
    Activations Density 0.455%

    No Known Activations