© 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. 59104
    Prev
    Next
    INDEX
    Explanations

    functions and purpose

    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
    åı¯æĥ³
    -0.09
    åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    è¿Ļæĸ¹éĿ¢
    -0.08
    ä»·æł¼ä¹Ł
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
     sogar
    -0.08
    åį´åıĪ
    -0.08
     theirs
    -0.08
    好åij¢
    -0.08
    igators
    -0.08
    POSITIVE LOGITS
    äºĮæĺ¯
    0.07
    èĤ¯å®ļè¦ģ
    0.07
     certes
    0.07
     âľĶ
    0.07
     grunds
    0.07
    åŁºæľ¬ä¿¡æģ¯
    0.07
    åĩ¡æľ¬ç½ij注æĺİ
    0.07
     vs
    0.06
    ien
    0.06
     ugyanis
    0.06
    Activations Density 0.304%

    No Known Activations