© 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. 34963
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    lys
    -0.08
    å®ľ
    -0.06
    ä¿¡
    -0.06
    äºĭä¸ļ
    -0.06
     Mountain
    -0.06
    اش
    -0.06
     conver
    -0.06
     ex
    -0.06
    èĮĹ
    -0.06
     prem
    -0.06
    POSITIVE LOGITS
    亲身
    0.08
    ä»İçİ°åľ¨å¼Ģå§ĭ
    0.08
    assis
    0.08
    imak
    0.08
    ç´łè´¨åĴĮ
    0.08
    akon
    0.07
    etim
    0.07
    漪
    0.07
    ezas
    0.07
    _BEGIN
    0.07
    Activations Density 0.000%

    No Known Activations