© 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. 59999
    Prev
    Next
    INDEX
    Explanations

    multiplication and addition in algebra

    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
    ä¸Ī
    -0.07
    å®ł
    -0.06
    ous
    -0.06
    æĮīæľŁ
    -0.06
    fad
    -0.05
    å°ıèħ¹
    -0.05
     os
    -0.05
     kapas
    -0.05
    çĽĪ
    -0.05
    alah
    -0.05
    POSITIVE LOGITS
    acket
    0.10
    oggi
    0.08
    æľ¬éĻ¢è®¤ä¸º
    0.08
    符æĸĩ
    0.08
    ä¾łä¼ł
    0.07
    à¹Ģละ
    0.07
    ابر
    0.07
    acle
    0.07
    æĪĸå¤ļ个
    0.07
    oke
    0.07
    Activations Density 0.011%

    No Known Activations