© 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. 32952
    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
    交æĺĵä¸Ń
    -0.07
     underlying
    -0.07
    åĩĿåĽº
    -0.06
     Ùħرج
    -0.06
     trembling
    -0.06
    å¸ĺ
    -0.06
    atan
    -0.06
    家åºŃçĶŁæ´»
    -0.06
     MST
    -0.05
    oudre
    -0.05
    POSITIVE LOGITS
    /mark
    0.12
    å®£ä¼ł
    0.12
     outreach
    0.11
    marketing
    0.11
    кеÑĤин
    0.11
    vertising
    0.11
     campaigns
    0.11
     пÑĢодви
    0.11
    å®£ä¼łåĴĮ
    0.11
     aggressively
    0.10
    Activations Density 0.271%

    No Known Activations