© 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. 44142
    Prev
    Next
    INDEX
    Explanations

    square root expressions

    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
    croft
    -0.10
    ajib
    -0.09
    uder
    -0.08
    arro
    -0.08
    -setup
    -0.08
    á»IJ
    -0.08
    设计çļĦ
    -0.08
     Digitale
    -0.08
    设计åĩº
    -0.08
     خاÙĨ
    -0.08
    POSITIVE LOGITS
    欺
    0.07
    æĮ¡
    0.06
    人æīĭ
    0.06
     inclin
    0.06
     vist
    0.06
     kn
    0.06
    å¤ļæĥ³
    0.06
    åµĮ
    0.06
    æĸĩä»¶æł¼å¼ı
    0.06
    ikel
    0.06
    Activations Density 0.002%

    No Known Activations