© 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. 46244
    Prev
    Next
    INDEX
    Explanations

    facilitate

    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
    /edit
    -0.07
    åīijæ°Ķ
    -0.07
    lation
    -0.07
    åĬłä»¥
    -0.07
    äºĪ以
    -0.06
    ĵ
    -0.06
    éľİ
    -0.06
    æĶ¯æŁ±äº§ä¸ļ
    -0.06
    ási
    -0.06
    isure
    -0.06
    POSITIVE LOGITS
     viá»ĩc
    0.10
    åĴĮè§ĦèĮĥ
    0.10
    à¸ģาร
    0.09
    å½¢ãģ§
    0.09
    å·¥ä½ľçļĦå¼Ģå±ķ
    0.09
    æ´»åĬ¨çļĦå¼Ģå±ķ
    0.09
    åIJİç»ŃçļĦ
    0.08
     subsequent
    0.08
    ä¹ŁæľīåĪ©äºİ
    0.08
     ìĤ¬ìļ©ìĿĦ
    0.08
    Activations Density 0.130%

    No Known Activations