© 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. 55920
    Prev
    Next
    INDEX
    Explanations

    priority queue and heap

    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
    é£İéĻ©åĪĨæŀIJ
    -0.08
     veloc
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.07
    enames
    -0.07
    æĹłæĤĶ
    -0.07
    é£İéĻ©èĩªæĭħ
    -0.07
    宿
    -0.07
    eties
    -0.07
    æ¶ĪéĢĢ
    -0.07
    财产å®īåħ¨
    -0.07
    POSITIVE LOGITS
    _heap
    0.08
    ä¸įåħ¥
    0.08
     heapq
    0.07
    æīĵåħ¥
    0.07
    heap
    0.07
    解æĶ¾
    0.07
    store
    0.07
     Kole
    0.07
    dee
    0.07
    _HEAP
    0.07
    Activations Density 0.004%

    No Known Activations