© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34891
    Prev
    Next
    INDEX
    Explanations

    coagulation, anticoagulant

    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
    Negative Logits
     Steam
    -0.07
     steam
    -0.07
    èĴ¸
    -0.07
    اÙĨÙĩ
    -0.07
    è¡Ľ
    -0.07
    åĮĸçŁ³
    -0.07
    èĴ¸èĴ¸
    -0.06
    Burn
    -0.06
    è¿ĽéĢĢ
    -0.06
    _android
    -0.06
    POSITIVE LOGITS
     clot
    0.14
    åĩĿè¡Ģ
    0.12
     antico
    0.10
     blood
    0.10
    åĩºè¡Ģ
    0.10
     throm
    0.09
    è¡ĢæµĨ
    0.09
    æIJı
    0.09
    æŃ¢è¡Ģ
    0.09
    è¡Ģå°ıæĿ¿
    0.09
    Activations Density 0.199%

    No Known Activations