© 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. 50920
    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
    æݥ踵
    -0.07
    第ä¸Ģ线
    -0.07
    缸å½ĵäºİ
    -0.07
    ä¹ĭ书
    -0.06
    è¢ĭ
    -0.06
    åĴĮæĥħæĦŁ
    -0.06
    agers
    -0.06
     Gems
    -0.06
    igel
    -0.06
    zers
    -0.06
    POSITIVE LOGITS
    åĽ¾æ¡Ī
    0.10
     motifs
    0.09
     motif
    0.09
    -themed
    0.08
    主é¢ĺçļĦ
    0.08
    ãĥ¢ãĥģãĥ¼ãĥķ
    0.08
    aisons
    0.08
    éĢłåŀĭ
    0.08
     passant
    0.08
    åľĸæ¡Ī
    0.08
    Activations Density 0.139%

    No Known Activations