© 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. 14063
    Prev
    Next
    INDEX
    Explanations

    infrastructure investments or programs

    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
    å¢ħ
    -0.09
    ạt
    -0.08
    unj
    -0.08
    zimmer
    -0.07
    òng
    -0.07
     ÐŀÑĤеÑĩеÑģÑĤвен
    -0.07
    nun
    -0.06
     gehouden
    -0.06
    ropping
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    POSITIVE LOGITS
    建设çļĦ
    0.13
    建设åĴĮ
    0.12
     infrastructure
    0.11
    rastructure
    0.11
    åŁºç¡Ģ设æĸ½
    0.10
    建è¨Ń
    0.10
    Infrastructure
    0.09
     اÙĦتØŃتÙĬØ©
    0.09
    设æĸ½
    0.09
    rement
    0.08
    Activations Density 0.054%

    No Known Activations