© 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. 44844
    Prev
    Next
    INDEX
    Explanations

    connection and bonding

    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
     redund
    -0.07
    梦
    -0.06
    ä¸įæĸŃä¼ĺåĮĸ
    -0.06
    ãģĦãĤį
    -0.06
    .persistence
    -0.06
    สà¸Ķ
    -0.06
    aina
    -0.06
    ä¸ĢåĪĩ
    -0.06
    ç¹ģå¤ļ
    -0.06
    conde
    -0.06
    POSITIVE LOGITS
     باÙĦÙĦÙĩ
    0.10
    ัà¸Ħ
    0.08
    çļĦ建ç«ĭ
    0.08
    æµħæµħ
    0.08
    боле
    0.08
    çļĦå½¢æĪIJ
    0.08
     поко
    0.08
    -building
    0.08
    éĨ¸
    0.08
     lewat
    0.08
    Activations Density 0.027%

    No Known Activations