© 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. 51968
    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
     disqualified
    -0.08
     пÑĢеÑĤен
    -0.08
    ceil
    -0.08
    ä¿Ŀéĩį
    -0.07
    æī¿éĩį
    -0.07
    æľŁéĹ´
    -0.07
    èıı
    -0.07
    achs
    -0.07
    å¤ĦçIJĨæĸ¹æ³ķ
    -0.07
    _frequency
    -0.07
    POSITIVE LOGITS
     favorable
    0.08
     overall
    0.08
    åĪ©çļĦ
    0.08
    _invoke
    0.08
    æľīåĪ©çļĦ
    0.08
     downhill
    0.08
     favor
    0.08
    æĢ»ä½ĵä¸Ĭ
    0.07
     favourable
    0.07
    æľīåĪ©
    0.07
    Activations Density 0.009%

    No Known Activations