© 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. 7576
    Prev
    Next
    INDEX
    Explanations

    drag coefficient, vortex street, SwiftUI Kit, excess magnetization

    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
    oca
    -0.08
     gác
    -0.07
    è´¨çļĦ
    -0.07
    ĵĴ
    -0.07
    åıijåĩºä¸Ģ
    -0.07
    ouro
    -0.07
     desf
    -0.07
    åıijåĩºäºĨ
    -0.07
    igar
    -0.06
    åĿĢ
    -0.06
    POSITIVE LOGITS
    éļı
    0.07
    çİĩåĴĮ
    0.07
    ikip
    0.07
    eil
    0.07
     empirical
    0.07
    çİĩ
    0.07
    æĽ³
    0.07
    å½Ĵ
    0.07
    aley
    0.06
    èµ·æīĭ
    0.06
    Activations Density 0.001%

    No Known Activations