© 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. 17438
    Prev
    Next
    INDEX
    Explanations

    heap; build-heap; priority_queue

    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
    angg
    -0.07
    mes
    -0.07
    macro
    -0.07
    aits
    -0.07
    AINS
    -0.07
    %B
    -0.06
    gnore
    -0.06
    _macro
    -0.06
    ipi
    -0.06
    æĸ½å·¥è¿Ľåº¦
    -0.06
    POSITIVE LOGITS
    ä¸į满
    0.08
    åıĹçIJĨåIJİ
    0.08
    å¥ļ
    0.08
    èĢģå¤ĸ
    0.07
    ç»´æĮģ
    0.07
    çİīå±±
    0.07
    ouston
    0.07
    weiler
    0.07
    otre
    0.07
    heap
    0.07
    Activations Density 0.005%

    No Known Activations