© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32213
    Prev
    Next
    INDEX
    Explanations

    excess, elevated, growth, nutrition

    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
    æĩ¦
    -0.08
    ä½İå¼Ģ
    -0.07
    anan
    -0.07
    å¼±èĢħ
    -0.07
    å¼±çļĦ
    -0.07
    æĩ¦å¼±
    -0.07
    æĮª
    -0.07
    æľĢå·®
    -0.07
    lag
    -0.07
    èĭ¦è¾£
    -0.07
    POSITIVE LOGITS
     excess
    0.20
     excessive
    0.18
     exces
    0.17
     избÑĭ
    0.16
    è¿ĩ度çļĦ
    0.16
    è¿ĩ度
    0.16
     berlebihan
    0.16
     ÑĩÑĢезмеÑĢ
    0.15
    è¿ĩåī©
    0.15
    è¿ĩéĩı
    0.15
    Activations Density 0.246%

    No Known Activations