© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21590
    Prev
    Next
    INDEX
    Explanations

    dates and authors

    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
    ä½ķåħ¶
    -0.09
    ä½ķä¸į
    -0.09
    ัà¸ŀ
    -0.08
    æ¯Ķè¾ĥ好çļĦ
    -0.07
    æŁIJäºĽ
    -0.07
    è¯ķæĥ³
    -0.07
     whats
    -0.07
    osz
    -0.07
    icu
    -0.07
    mapping
    -0.07
    POSITIVE LOGITS
     itib
    0.07
     plain
    0.07
    ä¸Ĭä¹ĺ
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    empo
    0.06
    nowrap
    0.06
    æ·±åıĹ广大
    0.06
    åĴĮå·¥ä½ľ
    0.06
    urr
    0.06
    ¡´
    0.06
    Activations Density 0.087%

    No Known Activations