© 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. 16914
    Prev
    Next
    INDEX
    Explanations

    force and 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
    åħīæĺİ
    -0.07
     protected
    -0.07
     ausz
    -0.07
    chern
    -0.07
     Monetary
    -0.07
    CommandEvent
    -0.07
    رÙģØ©
    -0.07
    å¾Īè¾Ľèĭ¦
    -0.07
    åĨĮ
    -0.06
    åħī彩
    -0.06
    POSITIVE LOGITS
    åIJĪåĬĽ
    0.08
     force
    0.08
     accelerating
    0.08
    å¾ĹåĬĽ
    0.08
    ä¼ģä¸ļæıIJä¾Ľ
    0.08
    æĺ¯æݨåĬ¨
    0.08
     Hook
    0.08
    force
    0.08
     Force
    0.07
    åĬĽåĴĮ
    0.07
    Activations Density 0.002%

    No Known Activations