© 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. 7101
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and definitions

    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
     Lair
    -0.07
     ÙĪØ¢
    -0.07
     Lans
    -0.07
    è
    -0.06
    uristic
    -0.06
    üg
    -0.06
    stras
    -0.06
    gien
    -0.06
    à¹Ĥล
    -0.06
    æ¦Ĥè¦ģ
    -0.06
    POSITIVE LOGITS
    elih
    0.08
    _pel
    0.08
    ême
    0.08
    .choices
    0.08
    칸
    0.07
    ä¸Ĭå½ĵ
    0.07
    å®īæģ¯
    0.07
    astia
    0.07
    .tap
    0.07
    æĢªä¸įå¾Ĺ
    0.07
    Activations Density 0.003%

    No Known Activations