© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50081
    Prev
    Next
    INDEX
    Explanations

    testing and diagnostic equipment

    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
    nict
    -0.07
    æĶ«
    -0.07
    Processed
    -0.07
    çĶŁäº§åĬłå·¥
    -0.07
    éłĺ
    -0.07
    æıIJé«ĺåѦçĶŁ
    -0.07
    è¡Ģ红
    -0.07
    uber
    -0.07
    ç¯Ŀ
    -0.06
    é¢Ĩ
    -0.06
    POSITIVE LOGITS
     testing
    0.10
    æµĭéĩı
    0.10
    æµĭè¯ķ
    0.10
     tester
    0.10
    æµĭ
    0.10
     Tester
    0.09
    æ£Ģæµĭ
    0.09
     Testing
    0.09
     voltage
    0.09
    çļĦæ£Ģæµĭ
    0.09
    Activations Density 0.028%

    No Known Activations