© 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. 11403
    Prev
    Next
    INDEX
    Explanations

    enterprise software systems

    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
    çĶµè§Ĩæľº
    -0.07
    æīĵçģ«æľº
    -0.07
    åĪ¶å¤ĩæĸ¹æ³ķ
    -0.06
    ÛĮÙĩ
    -0.06
    èĥĨ
    -0.06
    länd
    -0.06
    ç§ijåѦçłĶ究
    -0.06
     altr
    -0.06
     youtube
    -0.06
    å¼ķ
    -0.06
    POSITIVE LOGITS
     systems
    0.12
    ç³»ç»ŁçļĦ
    0.10
     software
    0.10
     workflows
    0.10
    systems
    0.10
    éĽĨæĪIJ
    0.10
     system
    0.10
    çݰ代åĮĸçļĦ
    0.10
     workflow
    0.10
    çݰ代åĮĸ
    0.10
    Activations Density 0.431%

    No Known Activations