© 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. 63815
    Prev
    Next
    INDEX
    Explanations

    dynamic and active motion

    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
    æĹłè¨Ģ
    -0.08
    åİļçļĦ
    -0.07
    åİļåİļçļĦ
    -0.07
     lump
    -0.07
    odule
    -0.07
    åİļ
    -0.07
    ائÙĤ
    -0.07
    alc
    -0.07
    çĬ
    -0.06
    alat
    -0.06
    POSITIVE LOGITS
    ä¸įæģ¯
    0.18
    åĬ¨æĦŁ
    0.15
    æ´»è·ĥ
    0.14
    åĬ¨çļĦ
    0.14
    åĭķçļĦ
    0.14
    çļĦåĬ¨æĢģ
    0.14
    (dynamic
    0.13
    æ´»è·ĥçļĦ
    0.13
    åĬ¨èµ·æĿ¥
    0.13
     dynam
    0.13
    Activations Density 0.182%

    No Known Activations