© 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. 44571
    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
    à¸Ļà¸Ļ
    -0.08
     oda
    -0.08
    èij©
    -0.08
    rück
    -0.07
    ë¶
    -0.07
    ibri
    -0.07
    æĭīæĭī
    -0.07
    ä½łçľĭçľĭ
    -0.07
    ç¯ł
    -0.07
    éĻĢ
    -0.07
    POSITIVE LOGITS
    äºİä»Ĭå¹´
    0.06
    æŀķ
    0.06
     implies
    0.06
     vers
    0.06
     né
    0.06
    è´¼
    0.06
    åijĬ
    0.06
     imply
    0.06
    è³Ĭ
    0.06
     inform
    0.06
    Activations Density 0.000%

    No Known Activations