© 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. 42325
    Prev
    Next
    INDEX
    Explanations

    double or dual words

    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¸īèĢħ
    -0.11
    ä¸Ģ个个
    -0.09
    ä¸ĢçĤ¹ä¸Ģæ»´
    -0.09
    ä¸ī个åŃĹ
    -0.08
    人åıĹ伤
    -0.08
    åĴĮéĶĢåĶ®
    -0.08
    åĩłç»ı
    -0.08
    гна
    -0.08
    ä¸ĢæŃ¥æŃ¥
    -0.08
    ä¸Ģ次次
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.14
    åĴĮä¸ī
    0.10
     dual
    0.10
    åıĮ
    0.09
    æĪĸ以ä¸Ĭ
    0.09
    (Double
    0.08
    (double
    0.08
    ,double
    0.08
    åıĮéĩį
    0.08
    éĽĻ
    0.08
    Activations Density 0.169%

    No Known Activations