© 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. 16216
    Prev
    Next
    INDEX
    Explanations

    describes or announces

    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
    æį®
    -0.07
    çŁ¥åħ¶
    -0.07
    folge
    -0.07
    iski
    -0.07
    ngen
    -0.07
    spre
    -0.07
    endo
    -0.07
    GuidId
    -0.07
    /to
    -0.07
    isky
    -0.07
    POSITIVE LOGITS
     <<-
    0.08
     explicitly
    0.08
    explicit
    0.08
    uhl
    0.07
     liken
    0.07
    æĺİç¡®æĮĩåĩº
    0.07
    æĻ
    0.07
    æĺİç¡®
    0.07
    mtx
    0.06
    วà¹Īา
    0.06
    Activations Density 0.003%

    No Known Activations