© 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. 41232
    Prev
    Next
    INDEX
    Explanations

    electrodes and surfaces

    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
    flation
    -0.08
    æĪIJ份
    -0.08
    .pkg
    -0.07
     puff
    -0.07
    çī¹èѦ
    -0.07
    çĥĪçģ«
    -0.07
    aley
    -0.07
    åĴĮ幸ç¦ı
    -0.07
    adies
    -0.07
    idden
    -0.07
    POSITIVE LOGITS
     surfaces
    0.11
    表éĿ¢
    0.10
    表éĿ¢çļĦ
    0.08
     surface
    0.08
     immersed
    0.08
    çī©çļĦ
    0.08
    æŀĹç«ĭ
    0.07
     Pov
    0.07
    æĿIJè´¨
    0.07
     Äijỡ
    0.07
    Activations Density 0.157%

    No Known Activations