© 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. 38036
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
    æĹ¥ä»¥æĿ¥
    -0.08
    anske
    -0.07
    åįķæĭĽ
    -0.07
    aternity
    -0.07
    ughs
    -0.07
    iranya
    -0.07
     Môn
    -0.07
    á»±
    -0.07
    detach
    -0.07
     Merke
    -0.06
    POSITIVE LOGITS
    preview
    0.07
    åı¬å¼ĢçļĦ
    0.06
    çļĦäºĭæĥħäºĨ
    0.06
    ment
    0.06
    arger
    0.06
    éħĭ
    0.06
    اÙħت
    0.06
    acci
    0.06
    ried
    0.06
    jo
    0.06
    Activations Density 0.053%

    No Known Activations