© 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. 4683
    Prev
    Next
    INDEX
    Explanations

    VEVENT, Service, nodelist{

    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
    ilai
    -0.08
    è´¹
    -0.07
    浩
    -0.07
     {@
    -0.07
     ""),
    -0.07
     "-",
    -0.07
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.07
     entgegen
    -0.07
    usc
    -0.07
    argas
    -0.07
    POSITIVE LOGITS
    ç½Ħ
    0.07
    æĻĵæĺİ
    0.07
     Bla
    0.07
    atism
    0.07
    almente
    0.06
    stil
    0.06
    etu
    0.06
    staan
    0.06
    éĥ½æĺ¯ä¸Ģ
    0.06
    ÏĢÏī
    0.06
    Activations Density 0.093%

    No Known Activations