© 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. 58887
    Prev
    Next
    INDEX
    Explanations

    performance, complications, outcomes, efficiency

    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
    å¦Ĥ约
    -0.08
    emani
    -0.08
    ãĥĵãĤ¢
    -0.07
    åı¯åĸľ
    -0.07
    ÙģÙĪر
    -0.07
    令
    -0.07
     Eins
    -0.07
    å¦Ĥçģ«
    -0.07
     [=
    -0.07
    دÙĦ
    -0.07
    POSITIVE LOGITS
    iddel
    0.08
    åĽłä¸ºæ²¡æľī
    0.07
    åĽłä¸ºæľī
    0.07
    åĽłä¸ºè¿Ļ个
    0.07
    åĽłä¸ºè¿ĻäºĽ
    0.07
    urious
    0.07
     because
    0.06
    å°±åĽłä¸º
    0.06
    æīĵæĿ¥
    0.06
    ord
    0.06
    Activations Density 0.118%

    No Known Activations