© 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. 25044
    Prev
    Next
    INDEX
    Explanations

    medical conditions and complications

    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
    ablish
    -0.07
    åĬŁèĥ½åĴĮ
    -0.07
    bou
    -0.07
    centes
    -0.07
    otive
    -0.07
     Äijuá»iji
    -0.07
    åĬĽæĮº
    -0.07
     عج
    -0.07
    ä½ļåIJį
    -0.07
    cto
    -0.07
    POSITIVE LOGITS
    åıijçĶŁåIJİ
    0.15
    åıijçĶŁæŶ
    0.14
     phenomenon
    0.13
    çݰ象
    0.13
     occurring
    0.12
    çļĦåıijçĶŁ
    0.12
    åıijçĶŁåľ¨
    0.12
     occurs
    0.12
    çı¾è±¡
    0.11
     occur
    0.11
    Activations Density 0.264%

    No Known Activations