© 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. 35016
    Prev
    Next
    INDEX
    Explanations

    open source

    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
    å®īæİĴ好
    -0.08
     Shopee
    -0.07
    ATR
    -0.07
    kest
    -0.07
    ä¼łå¯¼
    -0.07
    prud
    -0.07
    JNI
    -0.07
    ç¬ijè¯Ń
    -0.07
    /title
    -0.07
    仪
    -0.07
    POSITIVE LOGITS
     libre
    0.13
    å¼ĢæºIJ
    0.12
     freely
    0.12
     open
    0.11
    å¼ĢæĶ¾
    0.10
    /open
    0.10
    å¼ĢæĶ¾çļĦ
    0.10
    open
    0.10
     openly
    0.10
    èĩªçĶ±
    0.10
    Activations Density 0.633%

    No Known Activations