© 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. 25172
    Prev
    Next
    INDEX
    Explanations

    solve problems/solutions

    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
    صار
    -0.07
    å§Ĺ
    -0.07
    æĿ¥éĻ¢
    -0.07
     лиÑĤеÑĢ
    -0.07
     activated
    -0.07
    omma
    -0.06
    éĽģ
    -0.06
    éĩij森
    -0.06
    森
    -0.06
     Gecko
    -0.06
    POSITIVE LOGITS
    æķ´ä¸ªéĹ®é¢ĺ
    0.08
    ØŃÙĦØ©
    0.08
    imir
    0.07
     меÑĤодом
    0.07
    çİĩä½İ
    0.07
     بطرÙĬÙĤØ©
    0.07
    æѤä¸Ģ
    0.07
    解
    0.07
    ÐŀÐł
    0.07
    otron
    0.06
    Activations Density 0.054%

    No Known Activations