© 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. 4728
    Prev
    Next
    INDEX
    Explanations

    medical institutions, corn milling, living cells, stamps

    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
    Å¡t
    -0.07
    æѦç¥ŀ
    -0.07
    anns
    -0.07
    CF
    -0.07
    оÑĩно
    -0.07
    landet
    -0.07
    #__
    -0.07
    Via
    -0.07
    zh
    -0.06
    wayne
    -0.06
    POSITIVE LOGITS
    çĺª
    0.07
    çģ¸
    0.07
    æĦ
    0.07
    çĪ¹
    0.06
    uma
    0.06
    aider
    0.06
    Ùħاء
    0.06
    è¸Ĭè·ĥ
    0.06
    å¿ĥ仪
    0.06
     inf
    0.06
    Activations Density 0.229%

    No Known Activations