© 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. 55126
    Prev
    Next
    INDEX
    Explanations

    apply to

    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
    åIJ«
    -0.07
     unic
    -0.07
    ilas
    -0.06
    ÑĨÑı
    -0.06
    åĩ¡
    -0.06
    ä¿Ĺ
    -0.06
    轩
    -0.06
    åħ¬å¼ı
    -0.06
    _formula
    -0.06
     sis
    -0.06
    POSITIVE LOGITS
    iegel
    0.08
    voud
    0.08
    arry
    0.08
    leve
    0.07
    iples
    0.07
    å°±åĥıä¸Ģ个
    0.07
    ìķ
    0.07
    elter
    0.07
    åĽ¾åĨĮ
    0.07
    rray
    0.07
    Activations Density 0.038%

    No Known Activations