© 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. 29088
    Prev
    Next
    INDEX
    Explanations

    lens, glasses, optics

    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
    åħ»æĪIJäºĨ
    -0.07
    fir
    -0.07
    æīĵä¸Ĭ
    -0.07
    æµ·åĨħå¤ĸ
    -0.07
    tie
    -0.07
    ness
    -0.07
    éĿ¢èī²
    -0.07
    åĽ¾ç½ij
    -0.07
    建ç«ĭå®ĮåĸĦ
    -0.07
    ä¸ĢéŨ
    -0.07
    POSITIVE LOGITS
    arla
    0.07
    ä½ľçĶ¨
    0.07
     acting
    0.07
    osci
    0.06
     Acting
    0.06
     applied
    0.06
    	core
    0.06
    Luc
    0.06
     optics
    0.06
    è¯ĨåŃĹ
    0.06
    Activations Density 0.001%

    No Known Activations