© 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. 44354
    Prev
    Next
    INDEX
    Explanations

    first or end of year/season/round/state

    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
    ivate
    -0.09
    å¹³éĺ³
    -0.08
    zor
    -0.08
    linna
    -0.07
     rò
    -0.07
    çĸİ
    -0.07
     Farr
    -0.07
    abr
    -0.07
    ä¸įæį¢
    -0.07
    ITOR
    -0.07
    POSITIVE LOGITS
    并å®ĮæĪIJ
    0.08
    æĸ°è¯¾
    0.07
    ç´§æİ¥çĿĢ
    0.07
    æīįæĺ¯çľŁæŃ£çļĦ
    0.07
    éĽ¨éĽª
    0.07
     оÑĩеÑĢед
    0.07
    otec
    0.07
    fertig
    0.06
    cul
    0.06
    AMED
    0.06
    Activations Density 0.005%

    No Known Activations