© 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. 43562
    Prev
    Next
    INDEX
    Explanations

    temporal motion and dynamics

    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
    å±ħé«ĺ
    -0.08
    виа
    -0.07
    _Rem
    -0.06
    çªį
    -0.06
    affe
    -0.06
    .unit
    -0.06
    TK
    -0.06
    å°¾
    -0.06
    ä¸Ń度
    -0.06
    reme
    -0.06
    POSITIVE LOGITS
    åĬ¨æĢģ
    0.14
    çļĦåĬ¨æĢģ
    0.14
    åĭķæħĭ
    0.13
    dynamic
    0.13
     dynamic
    0.13
    (dynamic
    0.13
     dynam
    0.13
    åĭķçļĦ
    0.12
     дина
    0.12
    åĬ¨èµ·æĿ¥
    0.11
    Activations Density 0.266%

    No Known Activations