© 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. 59955
    Prev
    Next
    INDEX
    Explanations

    negative statements

    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
    éĢ¢
    -0.07
    intro
    -0.07
    hoe
    -0.07
    ÑĩаÑģÑĤи
    -0.07
    åĨħ容æĺ¯
    -0.06
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.06
    æĬĬéĤ£
    -0.06
     positively
    -0.06
    æĸĩåįİ
    -0.06
    å²Ĥä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
    æ²ī
    0.06
    ÙĪÙħÛĮ
    0.06
    upported
    0.06
     geçir
    0.06
    cratch
    0.06
    tere
    0.06
    моÑĢ
    0.06
    alles
    0.06
    ỳ
    0.06
    ä¸ĢæĦı
    0.06
    Activations Density 0.001%

    No Known Activations