© 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. 50429
    Prev
    Next
    INDEX
    Explanations

    topic, header, or subject titles

    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
    enne
    -0.08
    éĢļè¿ĩè¿ĻäºĽ
    -0.08
    sd
    -0.07
    å°¼æĸ¯
    -0.07
    zel
    -0.07
    天èµIJ
    -0.07
    ÏģοÏĨο
    -0.07
    kompl
    -0.07
    è¿ĻäºĽå°ı
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
    POSITIVE LOGITS
    群
    0.07
    Ìģ
    0.07
    uston
    0.07
    ursal
    0.06
    ix
    0.06
    主é¢ĺæĺ¯
    0.06
    çļĦ主é¢ĺ
    0.06
    UI
    0.06
    ggio
    0.06
     chart
    0.06
    Activations Density 0.102%

    No Known Activations