© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17978
    Prev
    Next
    INDEX
    Explanations

    abstract concepts visualization

    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
    ä¿Ŀå®Ī
    -0.08
    ultas
    -0.07
    æºĸ
    -0.07
    é¥®é£Łä¸Ĭ
    -0.07
    ì¤Ģ
    -0.07
    _survey
    -0.06
    çĭ¬ç«ĭèĩªä¸»
    -0.06
    اÙĤØ©
    -0.06
    ç¥Ŀç¦ıä½ł
    -0.06
     ì¤Ģ
    -0.06
    POSITIVE LOGITS
     vivid
    0.11
    çĶŁåĬ¨çļĦ
    0.11
    æĬ½è±¡
    0.11
    é²ľæ´»
    0.10
    缴è§Ĥ
    0.10
     ÙħÙĦÙħ
    0.10
    缴è§ĤçļĦæĸ¹å¼ı
    0.10
     Abstract
    0.10
     abstract
    0.10
    çĶŁåĬ¨
    0.09
    Activations Density 0.046%

    No Known Activations