© 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. 58849
    Prev
    Next
    INDEX
    Explanations

    html head tags and code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åįģä¸īç«ł
    -0.09
    åįģåħŃç«ł
    -0.07
    ijek
    -0.07
    Disposed
    -0.07
    Trad
    -0.07
    fts
    -0.07
    è°ģæĺ¯
    -0.07
    åįģä¹Ŀç«ł
    -0.07
    ymar
    -0.07
    åĿĩæĿ¥èĩªäºĴèģĶç½ij
    -0.07
    POSITIVE LOGITS
    æĢ¥
    0.07
     congrat
    0.06
    rex
    0.06
     accompanied
    0.06
     acknowledges
    0.06
    enhagen
    0.06
    fran
    0.06
     rex
    0.06
    缸åºĶ
    0.06
    raphe
    0.06
    Activations Density 0.005%

    No Known Activations