© 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. 8283
    Prev
    Next
    INDEX
    Explanations

    prototype, factors, gas, blog, press, Wikipedia, CBC

    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
    å±ķå¼Ģåħ¨æĸĩ
    -0.11
    okok
    -0.09
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.09
    ciuti
    -0.09
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.09
    缸åħ³æݨèįIJ
    -0.09
    æĶ¶èĹıæľ¬ç«Ļ
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    entifier
    -0.08
    åĢ¼å¾Ĺä¹°
    -0.08
    POSITIVE LOGITS
    å¼ı
    0.07
    ä¼łç»Ł
    0.07
    (
    0.07
    P
    0.06
    -
    0.06
    身åĪĨ
    0.06
    iser
    0.06
    M
    0.06
    /
    0.06
    [
    0.06
    Activations Density 1.017%

    No Known Activations