© 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. 24860
    Prev
    Next
    INDEX
    Explanations

    font family and size

    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
     Jin
    -0.07
    åīįåIJİ
    -0.06
    ink
    -0.06
    ستÙĩ
    -0.06
    ä¸Ģ度çļĦ
    -0.06
     mén
    -0.06
    à¹īà¸Ńà¸Ļ
    -0.06
     rein
    -0.06
    åIJģ
    -0.06
    reste
    -0.06
    POSITIVE LOGITS
    æŶéĹ´åĴĮ
    0.13
    é¢ľèī²åĴĮ
    0.12
    çļĦæŶéĹ´åĴĮ
    0.11
    æĸ¹åIJijåĴĮ
    0.11
    æŶéĹ´åıĬ
    0.11
    æķ°éĩıåĴĮ
    0.11
    ä¸įä»ħ
    0.11
    æĹ¢è¦ģ
    0.10
    æĹ¢ä¸į
    0.10
    ä¸įä»ħæľī
    0.10
    Activations Density 0.496%

    No Known Activations