© 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. 643
    Prev
    Next
    INDEX
    Explanations

    liver transplantation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    lod
    -0.07
     Poly
    -0.07
    kw
    -0.07
    彦
    -0.07
     Marr
    -0.07
    æ±Łè·¯
    -0.06
    omor
    -0.06
    stel
    -0.06
     aga
    -0.06
     заг
    -0.06
    POSITIVE LOGITS
    è¦ģäºĨ解
    0.07
     arbit
    0.07
    una
    0.07
    èĤĮ
    0.07
     uncon
    0.07
    igation
    0.07
    è¡·å¿ĥçļĦ
    0.07
    çݯç»ķ
    0.06
    Mismatch
    0.06
    å¿ĥåľ°
    0.06
    Activations Density 0.042%

    No Known Activations