© 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. 58891
    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
    åįİ缼
    -0.08
    å¼ĢçļĦ
    -0.07
    _scheme
    -0.07
    eload
    -0.07
    گار
    -0.07
    avan
    -0.07
     chém
    -0.07
     ÑĥÑģÑĤа
    -0.07
    zan
    -0.07
    lam
    -0.07
    POSITIVE LOGITS
     previously
    0.07
    鼷
    0.06
     ÑĢанее
    0.06
     سبÙĤ
    0.06
     contagious
    0.06
    rame
    0.06
     reun
    0.06
    reece
    0.06
    åľ¨å¥¹
    0.06
     previous
    0.06
    Activations Density 0.000%

    No Known Activations