© 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. 44848
    Prev
    Next
    INDEX
    Explanations

    alternative names

    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
    éĿŀ常æĺİæĺ¾
    -0.07
    senz
    -0.07
    çªģåĩº
    -0.07
    waan
    -0.07
    éĶĻçļĦ
    -0.06
     гоÑĢе
    -0.06
    æŶä¸Ģå®ļè¦ģ
    -0.06
    åīįæıIJæĺ¯
    -0.06
    apos
    -0.06
     voraus
    -0.06
    POSITIVE LOGITS
    ร
    0.08
    æĢĢæĬ±
    0.07
    Recorder
    0.07
    æĿIJ
    0.07
     nuanced
    0.06
    elda
    0.06
    äºĨçĤ¹
    0.06
    па
    0.06
    ä¸įæĢ¥
    0.06
    bsd
    0.06
    Activations Density 0.002%

    No Known Activations