© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 724
    Prev
    Next
    INDEX
    Explanations

    but it

    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
    Negative Logits
    notated
    -0.08
    ipment
    -0.08
    å¹´èİ·
    -0.08
    æĬĺä¸į
    -0.07
     ÐĿико
    -0.07
    عدÙĬد
    -0.07
    交æīĢ
    -0.07
    orem
    -0.07
    -Col
    -0.07
    oces
    -0.07
    POSITIVE LOGITS
     οÏĢοία
    0.07
    lain
    0.07
    bidden
    0.07
    注æĦıçļĦæĺ¯
    0.07
    èĢĮ论
    0.07
    å¦ĤæѤä¸ĢæĿ¥
    0.07
    صار
    0.06
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.06
    หà¹Į
    0.06
    èĢĮè¨Ģä¹ĭ
    0.06
    Activations Density 0.018%

    No Known Activations