© 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. 58797
    Prev
    Next
    INDEX
    Explanations

    is compact

    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
    é»Ħç´ł
    -0.08
    ãĥ¬ãĥĥ
    -0.08
    ÃŁer
    -0.08
     forfait
    -0.08
    áĥŃ
    -0.08
    عÙĩ
    -0.08
    ä½ĵå¼ı
    -0.07
    ä»ħä»£è¡¨ä½ľèĢħæľ¬äºº
    -0.07
    è¾ĥä½İçļĦ
    -0.07
    _detach
    -0.07
    POSITIVE LOGITS
     locally
    0.07
    åı¯
    0.06
     Ø®ÙĪØ´
    0.06
    _*
    0.06
    p
    0.06
     self
    0.06
     moreover
    0.06
     Kaz
    0.06
     <<-
    0.06
    éħİ
    0.06
    Activations Density 0.033%

    No Known Activations