© 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. 595
    Prev
    Next
    INDEX
    Explanations

    system/systemd/dot/novel/0

    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
     Pej
    -0.08
    empf
    -0.07
    ä¸Ģçīĩçīĩ
    -0.07
    æľīäºĭ
    -0.07
    adó
    -0.07
    <decltype
    -0.07
    atora
    -0.07
    ancer
    -0.07
    èİ«åıĬ
    -0.07
    ÃŃt
    -0.07
    POSITIVE LOGITS
     equations
    0.08
    ean
    0.07
     solved
    0.07
    eau
    0.06
    ulle
    0.06
    ä¾£
    0.06
    ickers
    0.06
     franco
    0.06
    æĪIJåIJį
    0.06
    Ñĥже
    0.06
    Activations Density 0.004%

    No Known Activations