© 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. 35041
    Prev
    Next
    INDEX
    Explanations

    links to

    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
    é«ĺ级模å¼ı
    -0.08
    мÑģ
    -0.07
    -addon
    -0.07
    订éĺħåı·
    -0.07
    quir
    -0.07
    gere
    -0.07
    UMENT
    -0.07
    gesteld
    -0.07
    æİĮä¸Ĭ
    -0.07
    (Font
    -0.07
    POSITIVE LOGITS
    éĵ¾æİ¥
    0.13
     links
    0.13
     link
    0.12
    /link
    0.11
    links
    0.10
     Links
    0.10
    -links
    0.10
    _links
    0.10
     Link
    0.10
     ë§ģíģ¬
    0.09
    Activations Density 0.189%

    No Known Activations