© 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. 11129
    Prev
    Next
    INDEX
    Explanations

    electrical, mechanical, or flex components

    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¸İä¹ĭ
    -0.06
    ÙĪج
    -0.06
    à¤Ĺà¥Ģ
    -0.06
    åѦèĢĮ
    -0.06
    管çIJĨä¸İ
    -0.06
    å®ĥ们æĺ¯
    -0.06
    ä¸īäºĶ
    -0.06
    å°ıå±±
    -0.06
    powered
    -0.06
    нÑģ
    -0.06
    POSITIVE LOGITS
     alike
    0.13
    æľīåĪ«
    0.11
    并举
    0.11
    åķıãĤıãģļ
    0.11
    ä¹ĭåĪĨ
    0.10
    åIJĪä¸Ģ
    0.10
    çļĨåı¯
    0.10
    çļĨæľī
    0.10
    çļĨ
    0.10
    ä¹ĭåĪ«
    0.09
    Activations Density 0.019%

    No Known Activations