© 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. 24950
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    人人
    -0.08
    为æıIJé«ĺ
    -0.08
    åIJijæĤ¨
    -0.07
     Impro
    -0.06
    åIJĮäºĭ们
    -0.06
     ÐĴа
    -0.06
    伯ä¹IJ
    -0.06
    amal
    -0.06
    ãĢĭ
    -0.06
    åħ¶ä¸º
    -0.06
    POSITIVE LOGITS
    oro
    0.08
    ç«ŀ
    0.07
    inee
    0.07
    èł
    0.07
    du
    0.07
    梳
    0.07
    inde
    0.07
    agan
    0.07
    rpc
    0.07
    æĢ»åĢ¼
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.