© 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. 2332
    Prev
    Next
    INDEX
    Explanations

    latest / recent / specific entities

    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
    æĪIJç«ĭçļĦ
    -0.07
    åľ¨åŃ¦ä¹ł
    -0.07
     afterward
    -0.06
    第ä¸Ģ项
    -0.06
    äºĭåħĪ
    -0.06
    第ä¸ĢæŃ¥
    -0.06
    第ä¸Ģ天
    -0.06
    ç«£
    -0.06
    oux
    -0.06
    æĹ©ä¸Ĭ
    -0.06
    POSITIVE LOGITS
     latest
    0.17
    latest
    0.15
    çļĦæľĢæĸ°
    0.15
    æľĢæĸ°çļĦ
    0.15
    æľĢæĸ°
    0.15
    _latest
    0.14
     recent
    0.14
     Latest
    0.14
    ä»Ĭå¹´çļĦ
    0.14
    /latest
    0.14
    Activations Density 1.266%

    No Known Activations