© 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. 4699
    Prev
    Next
    INDEX
    Explanations

    formula, Formula, fórmula

    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
    绣
    -0.06
    ipse
    -0.06
    CN
    -0.06
     Composition
    -0.06
    %
    -0.06
     Anal
    -0.06
    æİ©
    -0.06
    %'
    -0.06
     mut
    -0.06
    æıIJçIJ´
    -0.06
    POSITIVE LOGITS
    åħ¬å¼ı
    0.11
     formula
    0.10
    Formula
    0.09
    计ç®Ĺåħ¬å¼ı
    0.09
    ein
    0.09
    formula
    0.09
    éĩijæ¡¥
    0.09
     fórmula
    0.08
     Formula
    0.08
    å¼ı设计
    0.08
    Activations Density 0.002%

    No Known Activations