© 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. 19092
    Prev
    Next
    INDEX
    Explanations

    Episcopal church dioceses

    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
    åIJĦçľģ
    -0.09
    åĽ½åĬ¡
    -0.08
    åIJĦè¡Į
    -0.08
    åIJĦ级æĶ¿åºľ
    -0.08
    以åIJİåĨį
    -0.08
    åıįèħIJ
    -0.08
    æĶ¿æ³ķå§Ķ
    -0.08
    çľģéķ¿
    -0.08
    åIJĦ级åIJĦéĥ¨éŨ
    -0.07
    åIJĦ大
    -0.07
    POSITIVE LOGITS
    åľ¨å½ĵåľ°
    0.10
    è¾ĸåĮº
    0.09
     setempat
    0.09
    è¾ĸåĮºåĨħ
    0.09
     local
    0.08
    æīĢåľ¨åľ°
    0.08
    æīĢåľ¨
    0.08
    åĴĮåİ¿
    0.08
    (Local
    0.07
    è¾ĸ
    0.07
    Activations Density 1.137%

    No Known Activations