© 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. 6995
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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
    سÙĩ
    -0.07
     بÙĨت
    -0.07
    YC
    -0.07
     DISCLAIMER
    -0.07
    uze
    -0.07
    为贯彻èIJ½å®ŀ
    -0.07
    èįŀ
    -0.07
    èĶ»
    -0.07
    %A
    -0.07
    æĺ¯çݰ代
    -0.07
    POSITIVE LOGITS
    åĪ°è¿ĻéĩĮ
    0.08
    èģĶåIJĪä¼ļ
    0.07
    å§
    0.07
    ç¼
    0.07
    elon
    0.07
    åĺ
    0.07
    éĺµ
    0.07
     Mam
    0.06
    Scoped
    0.06
    drivers
    0.06
    Activations Density 0.042%

    No Known Activations