© 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. 32786
    Prev
    Next
    INDEX
    Explanations

    band gap structure

    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
    寸
    -0.08
    idon
    -0.08
    abouts
    -0.08
    tabil
    -0.07
     Kese
    -0.07
    acute
    -0.07
     infl
    -0.07
     kai
    -0.07
    æ±Łæµ·
    -0.07
    åIJĮæ¯Ķåĩıå°ij
    -0.07
    POSITIVE LOGITS
     gap
    0.09
     gaps
    0.09
    gap
    0.09
    空éļĻ
    0.09
    -gap
    0.09
    æĿŁç¼ļ
    0.08
     vacancy
    0.08
    _GAP
    0.07
     kosong
    0.07
    éļĻ
    0.07
    Activations Density 0.002%

    No Known Activations