© 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. 48736
    Prev
    Next
    INDEX
    Explanations

    computing device application

    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
    èµĦ讯ç½ij
    -0.07
    åľ¨èIJ¥
    -0.07
    æĹ¥çĶŁ
    -0.07
    rets
    -0.07
    è²Ķ
    -0.07
    ाय
    -0.07
    æݨèįIJæľ¬ä¹¦
    -0.07
    kunde
    -0.06
    ogne
    -0.06
    _mut
    -0.06
    POSITIVE LOGITS
    osti
    0.07
    éĩijåŁİ
    0.07
    ıģ
    0.06
     Wirk
    0.06
    å·¨
    0.06
    çĵ®
    0.06
    av
    0.06
    met
    0.06
    æ¯Ķ以å¾Ģ
    0.06
    yg
    0.06
    Activations Density 0.095%

    No Known Activations