© 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. 7138
    Prev
    Next
    INDEX
    Explanations

    , because

    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
    åħ¨éĥ¨è¯Ħ论
    -0.07
    ibox
    -0.07
    æĥ³åĥı
    -0.07
    ÑĢони
    -0.07
    ächst
    -0.06
    åIJĽ
    -0.06
    å¤ļå°ij
    -0.06
    zil
    -0.06
    -0.06
    towe
    -0.06
    POSITIVE LOGITS
    yar
    0.08
    èī¯
    0.07
    unid
    0.07
    /layout
    0.07
    azin
    0.07
    _UNDEFINED
    0.07
    çļĦåħīèį£
    0.07
    /upload
    0.07
    ente
    0.07
    дей
    0.06
    Activations Density 0.002%

    No Known Activations