© 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. 50345
    Prev
    Next
    INDEX
    Explanations

    suppliers and vendors

    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
    为人们
    -0.08
    让人们
    -0.07
    onie
    -0.07
    ç»Ļ人们
    -0.07
    uret
    -0.06
    æ»ķ
    -0.06
     candidacy
    -0.06
    æĿĢ人
    -0.06
    使人
    -0.06
    å¶ĭ
    -0.06
    POSITIVE LOGITS
     suppliers
    0.14
    ä¾ĽåºĶåķĨ
    0.13
     supplier
    0.13
     sourcing
    0.11
     Suppliers
    0.11
    ä¾Ľè´§
    0.11
     Supplier
    0.11
    éĩĩè´Ń
    0.11
    Supplier
    0.10
    åİŁæĿIJæĸĻ
    0.10
    Activations Density 0.080%

    No Known Activations