© 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. 10888
    Prev
    Next
    INDEX
    Explanations

    relationship between X and Y

    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
    çĶ¨æĦı
    -0.06
    æļ¦
    -0.06
     ec
    -0.06
    æľīç¦ı
    -0.06
    åĽĽæĸ¹
    -0.06
    åı°ä¸Ĭ
    -0.06
    LT
    -0.06
    obil
    -0.06
     instead
    -0.06
    åijĹ
    -0.06
    POSITIVE LOGITS
     ÙĪبÙĬÙĨ
    0.14
    quals
    0.08
     âĨĶ
    0.08
     <->
    0.08
    ãĤĵãģ¨
    0.08
    é£ĺé£ĺ
    0.08
    ÏĢά
    0.08
     Dici
    0.07
    çļĦ好åĿı
    0.07
    ãģĹãģŁãģĵãģ¨
    0.07
    Activations Density 0.119%

    No Known Activations