© 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. 42823
    Prev
    Next
    INDEX
    Explanations

    engine, boulder, worm, chart, Emacs, application, Vim, valve, solution

    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
    åIJ¾
    -0.07
    æ²³å¸Ĥ
    -0.07
    enius
    -0.07
    enames
    -0.07
    riad
    -0.07
    客æĪ·çļĦéľĢæ±Ĥ
    -0.07
    为建设
    -0.06
    éľĢè¦ģåIJĮ
    -0.06
    殿
    -0.06
    éĵħ
    -0.06
    POSITIVE LOGITS
    -wide
    0.09
    ربÙĩ
    0.08
     ÙĥÙĦÙĩ
    0.08
    æķ´ä½ĵ
    0.08
     entire
    0.07
    èĭ¦å¿ĥ
    0.07
     overall
    0.07
    wide
    0.07
    æķ´ä¸ª
    0.07
    交åĪ°
    0.07
    Activations Density 0.097%

    No Known Activations