© 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. 37605
    Prev
    Next
    INDEX
    Explanations

    separate or independent groups

    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
    apro
    -0.07
    itter
    -0.07
    转æį¢
    -0.07
    éļIJ
    -0.07
    åıĺæĢģ
    -0.07
     embedded
    -0.07
    ugo
    -0.07
     ÙħÙĨز
    -0.06
     Nelson
    -0.06
    ita
    -0.06
    POSITIVE LOGITS
     separately
    0.12
    åįķçĭ¬çļĦ
    0.11
    åįķçĭ¬
    0.09
     оÑĤделÑĮно
    0.09
     independently
    0.08
     separate
    0.08
    resp
    0.08
    çĿ¿
    0.08
    ä¾Ŀæ³ķèĩªä¸»
    0.08
    çĭ¬ç«ĭ
    0.08
    Activations Density 0.109%

    No Known Activations