© 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. 30807
    Prev
    Next
    INDEX
    Explanations

    job offers or positions

    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
    ä¸Ģ代
    -0.07
    สัà¸ĩ
    -0.07
    ä½ı客
    -0.07
    elic
    -0.06
    éĿĻæŃ¢
    -0.06
    åĮĸçĺĢ
    -0.06
    åºĹéĵºç»ıèIJ¥èĢħ
    -0.06
    ixin
    -0.06
    éĨĴ
    -0.06
     truncated
    -0.06
    POSITIVE LOGITS
    å¿ĥ仪
    0.12
     coveted
    0.11
    梦å¯IJ以æ±Ĥ
    0.10
    ç«ŀäºīæ¿ĢçĥĪ
    0.10
     вакан
    0.09
     offer
    0.09
     lucrative
    0.08
     acceptance
    0.08
     accepting
    0.08
    è¿Ļä¸ªæľºä¼ļ
    0.08
    Activations Density 0.326%

    No Known Activations