© 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. 33914
    Prev
    Next
    INDEX
    Explanations

    patent references 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
    æľ¬ç«ĻæīĢæľī
    -0.10
    yntax
    -0.09
    å¯Ł
    -0.09
    vie
    -0.09
    plevel
    -0.08
    çī¹åĪ«å£°æĺİ
    -0.08
    rating
    -0.08
    漿
    -0.08
    URN
    -0.08
    AndWait
    -0.08
    POSITIVE LOGITS
    standard
    0.07
     liv
    0.06
     earlier
    0.06
    [
    0.06
    ear
    0.06
    erton
    0.06
    ant
    0.06
     standard
    0.06
    /
    0.06
     ant
    0.06
    Activations Density 0.023%

    No Known Activations