© 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. 37472
    Prev
    Next
    INDEX
    Explanations

    specific kinds of things

    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
    _projection
    -0.07
    ÄįÃŃ
    -0.07
    SharedPtr
    -0.07
    _comp
    -0.07
    adz
    -0.07
     دÛĮج
    -0.07
    ä¹ħèĢĮ
    -0.07
    _abs
    -0.06
    Fizz
    -0.06
    bcc
    -0.06
    POSITIVE LOGITS
    urah
    0.08
    ensem
    0.08
    edah
    0.07
    è¿Ļæĺ¯æĪij们
    0.07
     بÙĪدÙĨ
    0.07
    è¿Ļåı¯æĺ¯
    0.07
    æīįåı¯
    0.07
    她æīį
    0.07
     Muit
    0.07
     automatically
    0.06
    Activations Density 0.004%

    No Known Activations