© 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. 50795
    Prev
    Next
    INDEX
    Explanations

    band gap

    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
    ä¸įèĪį
    -0.08
    åľºéĿ¢
    -0.07
    è¾Ĺ转
    -0.07
     contingent
    -0.07
    潺
    -0.07
    ç½IJ
    -0.07
     contingency
    -0.07
    isia
    -0.07
    containers
    -0.06
    stuk
    -0.06
    POSITIVE LOGITS
     semiconductor
    0.09
    gap
    0.08
    -gap
    0.08
    éļĻ
    0.07
     hurd
    0.07
     Semiconductor
    0.07
     gap
    0.07
    åīª
    0.07
    ç¦ģ
    0.07
    è·ĥ
    0.07
    Activations Density 0.011%

    No Known Activations