© 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. 31575
    Prev
    Next
    INDEX
    Explanations

    linear motion and positioning systems

    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
    æ¼ıæ´ŀ
    -0.07
    éĩį
    -0.07
    sock
    -0.06
    æķŀ
    -0.06
    azon
    -0.06
    åѤç«ĭ
    -0.06
    缼çļĦ
    -0.06
    èĭ¦å¿ĥ
    -0.06
    Defaults
    -0.06
    ä¼łæĴŃ
    -0.06
    POSITIVE LOGITS
    éĻIJä½į
    0.13
    è¡Įç¨ĭ
    0.11
     movements
    0.11
     movement
    0.11
    ä½į移
    0.11
    Movement
    0.09
     piston
    0.09
     displacement
    0.09
     Movement
    0.09
    å¾Ģå¤į
    0.09
    Activations Density 0.163%

    No Known Activations