© 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. 52140
    Prev
    Next
    INDEX
    Explanations

    In simpler terms

    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
    ctype
    -0.07
    UnderTest
    -0.07
    åħ³å¤´
    -0.07
    ä¸Ģç»ıåıijçİ°
    -0.07
    ä¼ģä¸ļç±»åŀĭ
    -0.07
    cita
    -0.07
    args
    -0.07
     ذکر
    -0.07
    èĢ¿èĢ¿
    -0.07
     menun
    -0.07
    POSITIVE LOGITS
    ç®ĢåįķæĿ¥è¯´
    0.10
    çīĪ
    0.10
    çļĦæĦıæĢĿæĺ¯
    0.09
    éĢļä¿Ĺ
    0.09
    说çĻ½äºĨ
    0.09
    æį¢åı¥è¯Ŀ说
    0.09
     simply
    0.09
    大æĦı
    0.08
    Simply
    0.08
    çīĪçļĦ
    0.08
    Activations Density 0.099%

    No Known Activations