© 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. 6985
    Prev
    Next
    INDEX
    Explanations

    rationalization, HTML header, suffix -ing

    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
    åĸļ
    -0.08
    fus
    -0.07
    æľ¬èģĮ
    -0.07
    ekten
    -0.07
    ippets
    -0.07
    ×ķ×ķת
    -0.07
    ERAL
    -0.07
    isar
    -0.07
    ystone
    -0.07
    OrFail
    -0.07
    POSITIVE LOGITS
    æ´ŀ
    0.08
    iero
    0.07
    첨
    0.06
    åģļæ³ķ
    0.06
    lamour
    0.06
     Polit
    0.06
    èį¡
    0.06
    èµĦéĩijæĿ¥æºIJ
    0.06
    ÏĦικο
    0.06
     SSR
    0.06
    Activations Density 0.003%

    No Known Activations