© 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. 51877
    Prev
    Next
    INDEX
    Explanations

    class attribute or name

    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
    Not in Any Lists

    No Comments

    Negative Logits
    è©°
    -0.07
     Bat
    -0.07
    2
    -0.07
    1
    -0.06
    .createTextNode
    -0.06
    åŃĺ
    -0.06
    bat
    -0.06
    Bat
    -0.06
    tol
    -0.06
    (QObject
    -0.06
    POSITIVE LOGITS
     íĮ¨
    0.09
    íĮ¨
    0.08
    åIJİç¼Ģ
    0.08
    çıŃçļĦ
    0.08
    inski
    0.08
    ä¸ĢæĬ¹
    0.08
    çıŃ
    0.08
     circonst
    0.08
    itest
    0.07
    elage
    0.07
    Activations Density 0.097%

    No Known Activations