© 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. 40408
    Prev
    Next
    INDEX
    Explanations

    motion and speed

    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
    æķ°éĩıçļĦ
    -0.07
    wij
    -0.07
    &e
    -0.06
    æİĸ
    -0.06
    лам
    -0.06
    ìĺ¥
    -0.06
    etten
    -0.06
    ç°ĩ
    -0.06
    åŁºæľ¬åİŁçIJĨ
    -0.06
    åĨħ容åıĬ
    -0.06
    POSITIVE LOGITS
    elocity
    0.08
    ABL
    0.07
    æŶéĢŁ
    0.07
    éĢŁåº¦
    0.07
    ÑīеÑģÑĤво
    0.07
    æĸ¹åIJij
    0.07
     dirig
    0.07
     ë°©íĸ¥ìľ¼ë¡ľ
    0.07
    红è±Ĩ
    0.07
     misunderstand
    0.07
    Activations Density 0.006%

    No Known Activations