© 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. 59934
    Prev
    Next
    INDEX
    Explanations

    parts of a whole

    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
    楼ä¸Ĭ
    -0.08
    adian
    -0.07
    好åŃ©åŃIJ
    -0.07
    èĥĮæĻ¯çļĦ
    -0.07
     Abrams
    -0.07
    ANI
    -0.07
    èµ·æºIJäºİ
    -0.07
    ffff
    -0.07
    对å°ı
    -0.07
    wl
    -0.07
    POSITIVE LOGITS
    ofi
    0.08
    lanz
    0.07
    å°±æĺ¯æĪij
    0.07
     moc
    0.07
    _ATT
    0.07
    å¿ħçĦ¶
    0.07
    ầm
    0.07
    æĺ¾å¾Ĺå¾Ī
    0.07
    apt
    0.07
    çľģ
    0.07
    Activations Density 0.166%

    No Known Activations