© 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. 7798
    Prev
    Next
    INDEX
    Explanations

    oxygen, saturation, hypoxemia

    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
    æıIJçIJ´
    -0.08
     взима
    -0.07
    伸缩
    -0.07
    轻巧
    -0.07
    èĤļåŃIJéĩĮ
    -0.07
     Ajax
    -0.07
    éĿŀçī©è´¨
    -0.07
    æ´»æĢ§åĮĸ
    -0.07
    kmale
    -0.07
    itam
    -0.07
    POSITIVE LOGITS
     oxygen
    0.09
    æ°§
    0.08
     Oxygen
    0.08
     киÑģл
    0.08
    çĽijæĬ¤
    0.08
     ventilation
    0.07
     Ventil
    0.07
     zor
    0.07
     ventil
    0.07
    鶴
    0.07
    Activations Density 0.018%

    No Known Activations