© 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. 56551
    Prev
    Next
    INDEX
    Explanations

    indicated by

    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
     pháºŃn
    -0.08
    åĩºäºİ
    -0.07
    inks
    -0.07
    主ä½ĵç»ĵæŀĦ
    -0.07
    zum
    -0.06
    羣æŃ£çļĦ
    -0.06
    以æѤ
    -0.06
    æĺ¯æĿ¥èĩª
    -0.06
    ToProps
    -0.06
    eh
    -0.06
    POSITIVE LOGITS
    ä½ĵçİ°åľ¨
    0.09
    两个æĸ¹éĿ¢
    0.09
    ä¸Ģç³»åĪĹçļĦ
    0.09
    enek
    0.08
    表çİ°åľ¨
    0.08
    ÑĹ
    0.08
    æĦıçļĦ
    0.08
    æ·ĭæ¼ĵå°½èĩ´
    0.08
    éķ¿éĿĴ
    0.08
    otten
    0.08
    Activations Density 0.210%

    No Known Activations