© 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. 41358
    Prev
    Next
    INDEX
    Explanations

    Parenting support and rights

    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
    inkan
    -0.07
     Premi
    -0.07
    åľ¨åŃ¦ä¹łä¸Ń
    -0.07
    éļħ
    -0.07
    gili
    -0.07
     rewarded
    -0.06
    åľŁåľ°æĬµæĬ¼
    -0.06
     exposed
    -0.06
    ä¼łåħ¥
    -0.06
    é¼ĵèĪŀ
    -0.06
    POSITIVE LOGITS
    æĬļåħ»è´¹
    0.12
    离å©ļåIJİ
    0.09
    æİ¥éĢģ
    0.09
    对åŃ©åŃIJ
    0.08
    åŃIJ女çļĦ
    0.08
    åı¦ä¸Ģæĸ¹
    0.08
    åŃIJ女
    0.08
    åįķæĸ¹
    0.08
    üt
    0.08
    æĬļåħ»
    0.08
    Activations Density 0.012%

    No Known Activations