© 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. 56347
    Prev
    Next
    INDEX
    Explanations

    endocytosis

    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
     database
    -0.07
    æķ°æį®åºĵ
    -0.07
    eners
    -0.07
     Database
    -0.07
     DATABASE
    -0.07
    æķ°æį®åºĵä¸Ń
    -0.07
     interstate
    -0.06
     grie
    -0.06
     installed
    -0.06
     Sturm
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĬĬ
    0.08
    é£İæļ´
    0.08
     modalidades
    0.07
    orne
    0.07
     cie
    0.07
    è¿ĽçļĦ
    0.07
    åĽĬ
    0.07
    è¿Ļç§įæĸ¹å¼ı
    0.07
    两ç§įæĸ¹å¼ı
    0.07
    ondern
    0.07
    Activations Density 0.030%

    No Known Activations