© 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. 4671
    Prev
    Next
    INDEX
    Explanations

    mathematical numbers and concepts

    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
    讨
    -0.07
    .Sync
    -0.07
    bell
    -0.07
    endom
    -0.07
     جÙĨ
    -0.07
    ä¸įäºī
    -0.07
     factur
    -0.07
    æł¸ç®Ĺ
    -0.07
     WON
    -0.07
    fully
    -0.07
    POSITIVE LOGITS
    .jquery
    0.07
    blas
    0.07
    ürg
    0.07
     integers
    0.07
    誤
    0.07
    精度
    0.07
     Pad
    0.07
    ç»ıè´¸
    0.07
    å¾·æĭī
    0.06
     proximity
    0.06
    Activations Density 0.005%

    No Known Activations