© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22197
    Prev
    Next
    INDEX
    Explanations

    biggest, value

    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
    販
    -0.09
    åIJĥåIJĥ
    -0.08
    елей
    -0.08
    פ×Ļ
    -0.08
    ãĥ
    -0.08
     !**
    -0.08
    strup
    -0.08
    ×ij×ķר
    -0.08
    azes
    -0.07
    ãĤĦãģı
    -0.07
    POSITIVE LOGITS
    [,]
    0.06
    zinho
    0.06
    estro
    0.06
    å°Ķ
    0.06
    æīĭéĩĮ
    0.06
     [(
    0.06
     [
    0.06
    occhio
    0.05
    æĪĸèĢħæĺ¯
    0.05
     '
    0.05
    Activations Density 0.012%

    No Known Activations