© 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. 2742
    Prev
    Next
    INDEX
    Explanations

    complex medical terminology

    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
    æķ£
    -0.07
    UID
    -0.07
    æĦıæĢĿ
    -0.07
    é«ĺåĩº
    -0.07
    FA
    -0.07
     deliberately
    -0.06
    åı©
    -0.06
    åģĩ
    -0.06
    éĤ£ä¸ĢåĪ»
    -0.06
     consec
    -0.06
    POSITIVE LOGITS
    çī¹å®ļçļĦ
    0.08
     Bestimm
    0.08
     specific
    0.07
    дей
    0.07
    mong
    0.07
    æŃ¥æŃ¥é«ĺ
    0.07
    æłĹåŃIJ
    0.07
    unds
    0.07
    ouser
    0.07
     bestimmte
    0.07
    Activations Density 0.227%

    No Known Activations