© 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. 52191
    Prev
    Next
    INDEX
    Explanations

    combining and synergistic effects

    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¸ĢåĪ»
    -0.07
    éĹ¹
    -0.07
     captive
    -0.07
    vasti
    -0.07
    gne
    -0.07
    à¸Ĭี
    -0.07
     unilateral
    -0.07
    ä¸įæ¸Ŀ
    -0.07
    æĸ°ç½ij
    -0.07
    xad
    -0.07
    POSITIVE LOGITS
    åIJĪ
    0.19
    åIJĪ并
    0.18
     concaten
    0.17
     combining
    0.16
    æĭ¼æİ¥
    0.16
     combine
    0.16
     concatenate
    0.16
    åıłåĬł
    0.15
    èģĶåIJĪ
    0.15
    缸åĬł
    0.15
    Activations Density 0.277%

    No Known Activations