© 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. 3051
    Prev
    Next
    INDEX
    Explanations

    mathematical derivatives involving powers

    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
    £¼
    -0.07
    ustes
    -0.07
    åĪ°ä¼ļ
    -0.07
    uches
    -0.07
    uris
    -0.07
    达产年
    -0.07
    å¥
    -0.07
    é»Ħèī²çļĦ
    -0.06
    åįģåĪĨéĴŁ
    -0.06
    åŃ¦å£«åѦä½į
    -0.06
    POSITIVE LOGITS
    è¡ĢèĦī
    0.08
    éļľ
    0.08
    æıīäºĨ
    0.08
    ilet
    0.07
     fixed
    0.07
     ÑĦик
    0.07
    æłı
    0.07
     hab
    0.07
    vinc
    0.07
    inki
    0.07
    Activations Density 0.011%

    No Known Activations