© 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. 34043
    Prev
    Next
    INDEX
    Explanations

    government and public sector entities

    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
    åĮºå§Ķ书记
    -0.08
    å¸Ĥä¸Ń级人æ°ijæ³ķéĻ¢
    -0.07
    ç§ij主任
    -0.07
    /moment
    -0.07
    åħ¬åı¸æĢ»ç»ıçIJĨ
    -0.07
    æ½ľåħ¥
    -0.07
    pragma
    -0.07
    å°¾éħĴ
    -0.07
    èĶĵ
    -0.07
    ifest
    -0.07
    POSITIVE LOGITS
     government
    0.12
    åĴĮæĶ¿åºľ
    0.11
    åĴĮ人æ°ij
    0.11
    /public
    0.10
     official
    0.10
    -backed
    0.10
    å®ĺ
    0.10
     public
    0.10
    æĶ¿åºľ
    0.10
    .gov
    0.10
    Activations Density 0.589%

    No Known Activations