© 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. 44721
    Prev
    Next
    INDEX
    Explanations

    arguing for or with

    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
    Tower
    -0.07
    æĪijæĿ¥è¯´
    -0.06
    æĭ¿æĿ¥
    -0.06
    -automatic
    -0.06
    å¦ĸéŃĶ
    -0.06
     ÙĪÙĤبÙĦ
    -0.06
    orme
    -0.06
    空æ°Ķä¸Ń
    -0.06
    ä¿ij
    -0.06
    zec
    -0.06
    POSITIVE LOGITS
    åħ¬åı¸äºİ
    0.15
     بØŃÙĦÙĪÙĦ
    0.13
     ÙĦÙħدة
    0.13
    ä¸Ģ段æŶéĹ´åIJİ
    0.13
     throughout
    0.12
     ÙĦÙģترة
    0.12
     ÙħÙĨØ°
    0.12
     sooner
    0.11
    éĹ®é¢ĺæŶ
    0.11
     anytime
    0.11
    Activations Density 1.905%

    No Known Activations