© 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. 27975
    Prev
    Next
    INDEX
    Explanations

    lessons learned from reports

    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
    chie
    -0.08
    æľĢæĸ°æĽ´æĸ°
    -0.07
     irresist
    -0.07
     irresistible
    -0.07
    æļ§
    -0.07
    gree
    -0.07
    æĹ¥ä¹ħ
    -0.07
     Cint
    -0.07
     forcibly
    -0.07
     αÏĢ
    -0.07
    POSITIVE LOGITS
    æķĻè®Ń
    0.17
    åIJ¸åıĸ
    0.17
     lessons
    0.15
    åıįçľģ
    0.14
    æĢ»ç»ĵç»ıéªĮ
    0.14
     Lessons
    0.14
    å¤įçĽĺ
    0.13
    åıįæĢĿ
    0.13
    lessons
    0.13
    æ£Ģ讨
    0.13
    Activations Density 0.199%

    No Known Activations