© 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. 7036
    Prev
    Next
    INDEX
    Explanations

    gate, source, drain

    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
    çŁ
    -0.08
    sets
    -0.08
    Ãłm
    -0.08
     Deadline
    -0.07
    lez
    -0.07
    åħijçİ°
    -0.07
    rollo
    -0.07
    ueur
    -0.07
    enes
    -0.07
    åħħ
    -0.07
    POSITIVE LOGITS
    两级
    0.07
    jung
    0.07
    ลà¹Īาà¸ĩ
    0.07
    åĬ¡å®ŀ
    0.07
    ê¸Ģ
    0.07
    acus
    0.07
     hiz
    0.07
    ãģ£ãģĵ
    0.06
    è¡Įä¹ĭ
    0.06
    c
    0.06
    Activations Density 0.001%

    No Known Activations