© 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. 16359
    Prev
    Next
    INDEX
    Explanations

    license file

    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
    ITLE
    -0.07
    ä»İæѤ
    -0.07
    è¿ĶåĽŀé¦ĸ页
    -0.06
    bitrary
    -0.06
    /url
    -0.06
     Slot
    -0.06
    Slot
    -0.06
    arle
    -0.06
    olini
    -0.06
    erden
    -0.06
    POSITIVE LOGITS
    æĮīçħ§åĽ½å®¶
    0.08
     Decompiled
    0.08
    人ä¸Ń
    0.07
    RELEASE
    0.07
    æĺ¥åįİ
    0.07
    人马
    0.07
    çĤ¹ä¸ªèµŀ
    0.07
    éħįç½®æĸĩ件
    0.07
    .nc
    0.07
    ï½ŀãĢĤ
    0.07
    Activations Density 0.446%

    No Known Activations