© 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. 57110
    Prev
    Next
    INDEX
    Explanations

    xaml layout attributes

    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
    ettle
    -0.07
     relay
    -0.07
    жек
    -0.07
    宸
    -0.07
    Temp
    -0.06
    澡
    -0.06
    代表çļĦ
    -0.06
    çĥĻ
    -0.06
    atan
    -0.06
    wich
    -0.06
    POSITIVE LOGITS
    ä¸Ģèµ·åĪĨ享
    0.07
    astas
    0.07
     lej
    0.07
     teamed
    0.07
    ordion
    0.07
    å¾ħå®ļ
    0.07
    æĹ¥çĶŁ
    0.07
    asti
    0.06
    çķĻé¦Ļ
    0.06
    æİ¥ä¸ĭ
    0.06
    Activations Density 0.052%

    No Known Activations