© 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. 12878
    Prev
    Next
    INDEX
    Explanations

    Latin phrases and idioms

    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
    ijen
    -0.08
    å·¥ä½ľåľ¨
    -0.07
    åĭ»
    -0.07
    croft
    -0.07
    èĦIJ
    -0.06
    åĴ¯åĴ¯
    -0.06
    齡
    -0.06
    åįĬ
    -0.06
    عÙĪ
    -0.06
     urma
    -0.06
    POSITIVE LOGITS
    éĩĬä¹ī
    0.09
    éĢłåı¥
    0.09
    形容
    0.09
    åıįä¹īè¯į
    0.08
    éĢł
    0.07
    çļĦæĦıæĢĿ
    0.07
    æ¯Ķåĸ»
    0.07
    ujud
    0.07
    æĿ¥å½¢å®¹
    0.07
    åıĤèĢĥä»·æł¼
    0.07
    Activations Density 0.002%

    No Known Activations