© 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. 63735
    Prev
    Next
    INDEX
    Explanations

    SECRETARY OF HEALTH

    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
    æİ
    -0.07
    综
    -0.07
    åĴĮ第äºĮ
    -0.07
    룬
    -0.07
    èļģ
    -0.07
    ctor
    -0.07
    à¸Ńà¸ļ
    -0.07
     mast
    -0.06
    르íģ¬
    -0.06
    Friends
    -0.06
    POSITIVE LOGITS
    variably
    0.07
    reso
    0.07
    qi
    0.07
    dito
    0.07
    éľ¹éĽ³
    0.07
    olos
    0.07
    ãm
    0.07
    ä¸įæĢ¥
    0.07
    osing
    0.07
    æĸ¯åħĭ
    0.06
    Activations Density 0.032%

    No Known Activations