© 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. 54996
    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
    ermal
    -0.08
    ä¸İæĿİ
    -0.07
    accept
    -0.07
    áŀŁáŁĭ
    -0.07
     accept
    -0.07
    pond
    -0.07
     Nationals
    -0.07
    IPH
    -0.07
    (inter
    -0.07
    ere
    -0.07
    POSITIVE LOGITS
    isman
    0.07
    çīĩçīĩ
    0.06
    åīįåIJİ
    0.06
    ä¾ĦåŃIJ
    0.06
    \Active
    0.06
    [*
    0.06
    nga
    0.06
    iform
    0.06
    ä¸Ĭä¸ĭ
    0.06
    å°Ķ夫
    0.06
    Activations Density 0.000%

    No Known Activations