© 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. 29769
    Prev
    Next
    INDEX
    Explanations

    author names and citations

    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
    è¿ĺæĺ¯ä¸ª
    -0.08
    ä»Ĺ
    -0.08
    ä½ĵåĴĮ
    -0.07
    ×ĺ×Ļפ
    -0.07
    åĴĮä¸įèī¯
    -0.07
    åĴĮ对
    -0.07
     ÙĥÙĦÙĩ
    -0.07
    à¹ģละสà¹Īà¸ĩ
    -0.07
    çł´äºĨ
    -0.06
    anked
    -0.06
    POSITIVE LOGITS
     eds
    0.11
    éz
    0.07
    ãģ¨ãģĦãģ£ãģŁ
    0.07
    ä¸įæŁĵ
    0.07
     serta
    0.07
    å¥ķ
    0.07
    족
    0.07
    elius
    0.07
    LESS
    0.06
    endra
    0.06
    Activations Density 0.043%

    No Known Activations