© 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. 55071
    Prev
    Next
    INDEX
    Explanations

    addition or pairs

    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
    leden
    -0.07
    ç»·
    -0.07
    enez
    -0.07
    æĿ¡
    -0.07
    ohl
    -0.07
    à¸ģว
    -0.07
     Tow
    -0.07
    ubar
    -0.07
    åĪ©äºİ
    -0.07
     Habe
    -0.06
    POSITIVE LOGITS
     إضاÙģ
    0.09
     added
    0.09
    Addon
    0.08
    ضاÙģ
    0.08
     addition
    0.08
    ToAdd
    0.08
    é¢Ŀå¤ĸçļĦ
    0.08
     اÙĦإضاÙģ
    0.08
     additional
    0.08
    并åħ¥
    0.08
    Activations Density 0.006%

    No Known Activations