© 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. 2470
    Prev
    Next
    INDEX
    Explanations

    web addresses and URLs

    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
    LIA
    -0.07
    çªĸ
    -0.06
    å±ŀäºİ
    -0.06
     {}\
    -0.06
    ocking
    -0.06
    erves
    -0.06
    lia
    -0.06
     fur
    -0.06
    æĸĩç«łäºĨ
    -0.06
    ÑĦик
    -0.06
    POSITIVE LOGITS
    ipel
    0.08
    æĺ¨å¤©çļĦ
    0.08
    imedia
    0.07
    çĻ¾åIJį
    0.07
    INTERNAL
    0.07
    ijin
    0.07
    ÐļÑĢа
    0.07
    izza
    0.07
    nee
    0.07
    Modules
    0.07
    Activations Density 0.063%

    No Known Activations