© 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. 55502
    Prev
    Next
    INDEX
    Explanations

    cardiography, anesthetic, malaria

    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
    лиÑĩнÑĭе
    -0.06
    å¸Īå§IJ
    -0.06
    æļĸæļĸ
    -0.06
    L
    -0.06
    使çĶ¨åĴĮ
    -0.06
    ä»·æł¼åľ¨
    -0.06
    çŃīæīĭ段
    -0.05
    T
    -0.05
     complete
    -0.05
     Rob
    -0.05
    POSITIVE LOGITS
    viz
    0.10
    èĦļè¸ıå®ŀ
    0.09
    chine
    0.08
     Ø°ÙĬ
    0.08
    _DLL
    0.08
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    clés
    0.07
    WithType
    0.07
    åıĬéħį件
    0.07
    ä¹ĭæ¯į
    0.07
    Activations Density 0.273%

    No Known Activations