© 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. 37687
    Prev
    Next
    INDEX
    Explanations

    rate of conversion and turnover

    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
    ÑĩеÑĢед
    -0.07
    alloc
    -0.07
    ä¸ĢèĪ¬éľĢè¦ģ
    -0.07
    Ł
    -0.07
    ils
    -0.06
    .ali
    -0.06
    飬
    -0.06
    ÙħÙĪÙĦ
    -0.06
    irsch
    -0.06
    èµ°ä¸Ģèµ°
    -0.06
    POSITIVE LOGITS
    åIJĦ
    0.09
    errer
    0.08
    onta
    0.08
    éĢŁçİĩ
    0.08
     rates
    0.07
     opposing
    0.07
    imson
    0.07
    æĹ¥å¤ľ
    0.07
    éĢŁ
    0.07
    kaw
    0.07
    Activations Density 0.001%

    No Known Activations