© 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. 34861
    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
    ä¸ĭåĪĹ
    -0.07
    âĢ¦
    -0.07
    ắt
    -0.07
    åįķéĢī
    -0.07
    pone
    -0.07
    ToOne
    -0.07
     (âĢ¦)
    -0.06
    æ¯Ĥ
    -0.06
    éĢī项ä¸Ń
    -0.06
     à¸ķัวà¹Ģลืà¸Ńà¸ģ
    -0.06
    POSITIVE LOGITS
    auan
    0.07
    æĥ³æĸ¹
    0.07
    æĶ¾çŁ¢
    0.07
     Erb
    0.07
     Estudi
    0.07
    yan
    0.06
    åIJĥä¸į
    0.06
     Hay
    0.06
    oras
    0.06
    åħĥåĴĮ
    0.06
    Activations Density 0.000%

    No Known Activations