© 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. 58985
    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
    olino
    -0.08
    aton
    -0.07
    łĢ
    -0.07
    omon
    -0.07
    æŁ¥æĺİ
    -0.07
     deal
    -0.07
    беÑĤ
    -0.06
    jeÄį
    -0.06
    BT
    -0.06
     Deal
    -0.06
    POSITIVE LOGITS
     Hao
    0.07
    indsight
    0.07
    æĸĵ
    0.07
    é¢IJ
    0.07
    óm
    0.07
     vision
    0.06
    hão
    0.06
    æ°¸åĴĮ
    0.06
    heets
    0.06
    =sum
    0.06
    Activations Density 0.000%

    No Known Activations