© 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. 54937
    Prev
    Next
    INDEX
    Explanations

    complex quantitative scientific industrial application decision

    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
    spflicht
    -0.09
    kena
    -0.08
     saper
    -0.08
    OfMonth
    -0.08
    apor
    -0.08
    inals
    -0.08
    دÙĬÙħ
    -0.07
    ÙĤØ·
    -0.07
    ÏĢοÏĦε
    -0.07
    صÙģØ©
    -0.07
    POSITIVE LOGITS
    å¤įæĿĤçļĦ
    0.13
    å¤ļæł·çļĦ
    0.12
    å¤įæĿĤ
    0.12
    è¤ĩéĽij
    0.11
    èİ«æµĭ
    0.11
    è¤ĩ鼾
    0.11
    complex
    0.10
    å¤įæĿĤæĢ§
    0.10
     complexity
    0.10
    ç¨ĭ度
    0.09
    Activations Density 0.040%

    No Known Activations