© 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. 47401
    Prev
    Next
    INDEX
    Explanations

    when or while verbs

    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
    å·¥åķĨè¡ĮæĶ¿ç®¡çIJĨå±Ģ
    -0.07
    åľ¨åħ¶ä¸Ń
    -0.06
    åħĪåĪ°
    -0.06
    kana
    -0.06
    uggestion
    -0.06
    æ»ĭ
    -0.06
    etus
    -0.06
    å°ļ
    -0.06
    åľ¨è¢«
    -0.06
    wy
    -0.06
    POSITIVE LOGITS
     hendak
    0.10
    å¤ĦçIJĨåĴĮ
    0.09
    设计åĴĮ
    0.09
    éĺħè¯»æľ¬æĸĩ
    0.08
     designing
    0.08
    è¯Ħä»·
    0.08
    æĸ¹æ¡Ī设计
    0.08
    çIJĨ解åĴĮ
    0.08
    å¤ĦçIJĨ
    0.08
    ä¸Ĭè¦ģ
    0.08
    Activations Density 0.642%

    No Known Activations