© 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. 34996
    Prev
    Next
    INDEX
    Explanations

    post, share, caption, history

    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
     webb
    -0.07
    czy
    -0.07
    .bz
    -0.07
    eht
    -0.07
    ³³
    -0.07
    ³³³
    -0.07
    "..
    -0.07
    obiet
    -0.07
    راز
    -0.06
    ³³³³³³³
    -0.06
    POSITIVE LOGITS
    eri
    0.07
    æĮĩ导åĴĮ
    0.07
    缴è§ĤçļĦæĸ¹å¼ı
    0.06
    ouv
    0.06
    èµ°ä¸ĬäºĨ
    0.06
     segui
    0.06
    gegen
    0.06
    anchor
    0.06
    ãĢĤãĢĮ
    0.06
    æĹłéļľç¢į
    0.06
    Activations Density 0.077%

    No Known Activations