© 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. 48034
    Prev
    Next
    INDEX
    Explanations

    funding and support

    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
    tright
    -0.08
     Pilk
    -0.08
    ingos
    -0.07
    keh
    -0.07
    è¯ĨåĪ«åĽ¾ä¸ŃäºĮç»´çłģ
    -0.07
    æĸ°ä¹¦æݨèįIJ
    -0.07
    >Description
    -0.07
    arrant
    -0.07
    ä¸ĵä¸ļ人士
    -0.07
    çĮİ头
    -0.07
    POSITIVE LOGITS
     funding
    0.10
     funded
    0.08
     thanks
    0.08
     ÑĦинанÑģ
    0.07
    è°¢æĦı
    0.07
     partly
    0.07
     financ
    0.07
     grant
    0.07
     Funding
    0.07
    åıĮæĸ¹çļĦ
    0.07
    Activations Density 0.239%

    No Known Activations