© 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. 39691
    Prev
    Next
    INDEX
    Explanations

    research and science fields

    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
    upu
    -0.08
    稿件æĿ¥æºIJ
    -0.08
    volu
    -0.08
    ableObject
    -0.08
    IZER
    -0.08
    ritable
    -0.08
    annes
    -0.08
    ableView
    -0.08
    ensible
    -0.08
    icamente
    -0.08
    POSITIVE LOGITS
     theory
    0.12
    论è¯Ń
    0.10
     analysis
    0.09
    çIJĨ论
    0.09
     Theory
    0.09
    åѦåĴĮ
    0.09
    ศาสà¸ķรà¹Į
    0.09
    iology
    0.09
    åѦ
    0.08
    å¿ĥçIJĨåѦ
    0.08
    Activations Density 0.330%

    No Known Activations