© 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. 27936
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and names

    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
    sWith
    -0.10
    åĴĮ
    -0.10
    nya
    -0.10
    ingly
    -0.08
    åĴĮæľīåħ³
    -0.07
    aghetti
    -0.07
    ager
    -0.07
    çļĦ
    -0.07
    o
    -0.07
    sel
    -0.07
    POSITIVE LOGITS
    äºĨçļĦ
    0.11
    ãģĺãĤģãģ¦
    0.09
    äºĨä¸ĢåįĬ
    0.09
    ä¸įäºĨçļĦ
    0.09
    ä¸įå¼ĢçļĦ
    0.09
    à§įস
    0.09
    zione
    0.09
    ëı
    0.08
     lá»ıng
    0.08
    à§įম
    0.08
    Activations Density 0.002%

    No Known Activations