© 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. 44661
    Prev
    Next
    INDEX
    Explanations

    publishing rights documentation compliance

    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
    пей
    -0.08
    utoff
    -0.07
     contempora
    -0.07
    жава
    -0.07
    ç§ijåѦåѦéĻ¢
    -0.06
    太åIJİ
    -0.06
    Lookup
    -0.06
    ิศ
    -0.06
    çĦ¦æĢ¥
    -0.06
    ifel
    -0.06
    POSITIVE LOGITS
    èĮ
    0.07
    ¬
    0.07
     atten
    0.07
    箸
    0.06
     att
    0.06
    æįĮ
    0.06
    æį·
    0.06
    chu
    0.06
    att
    0.06
     зе
    0.06
    Activations Density 8.801%

    No Known Activations