© 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. 31330
    Prev
    Next
    INDEX
    Explanations

    E3 ubiquitin ligase

    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
     ende
    -0.08
    cript
    -0.07
    acen
    -0.07
    æĻĥ
    -0.07
    ubar
    -0.07
    å¦ĤåĽł
    -0.07
    åIJ¾
    -0.07
    osc
    -0.07
    elligence
    -0.06
    iez
    -0.06
    POSITIVE LOGITS
    วà¸Ķ
    0.08
    æī§è¡Įå®ĺ
    0.07
    åħ¼ãģŃ
    0.07
    ợ
    0.07
    'es
    0.07
    åĬŁåĭĭ
    0.07
    æļ´é£İ
    0.07
    åģĩæĹ¥
    0.07
    teras
    0.07
     ìĹ¼
    0.07
    Activations Density 0.001%

    No Known Activations