© 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. 25655
    Prev
    Next
    INDEX
    Explanations

    QCD, CP, SU(N), constituent, copyright

    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
    _EXIST
    -0.07
    éķĢ
    -0.07
    ãĥ©ãĥ³ãĤ¹
    -0.07
     cabel
    -0.07
     lol
    -0.07
    éĽªæ¢¨
    -0.07
    å¥ĩæīį
    -0.07
    lava
    -0.06
    Paint
    -0.06
    º¼
    -0.06
    POSITIVE LOGITS
    -boot
    0.08
    bloc
    0.07
     Levin
    0.07
    emus
    0.07
    Framework
    0.07
    attering
    0.07
    éĩį建
    0.07
    ảng
    0.07
    Ùĥت
    0.07
    arten
    0.07
    Activations Density 0.003%

    No Known Activations