© 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. 40129
    Prev
    Next
    INDEX
    Explanations

    you are / you thinking

    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¸įåİ»
    -0.06
    1
    -0.06
    è½
    -0.06
    å°±åĥıæĺ¯
    -0.05
     securely
    -0.05
    tra
    -0.05
    æĺİæĺİ
    -0.05
    num
    -0.05
    éĢĹ
    -0.05
    agina
    -0.05
    POSITIVE LOGITS
     someday
    0.09
    å·¥ä½ľå®ŀéĻħ
    0.08
    )this
    0.08
    à¹ĥà¸Ĭà¹īà¹Ģà¸Ľà¹ĩà¸Ļ
    0.08
    å¿Į讳
    0.08
    intai
    0.08
    å°ĨæĿ¥çļĦ
    0.08
    urgi
    0.08
    ä¸įåIJĮè§Ĵ度
    0.08
    æ¯ķç«Łæĺ¯
    0.08
    Activations Density 0.022%

    No Known Activations