© 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. 28581
    Prev
    Next
    INDEX
    Explanations

    incomplete combustion

    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
    ongen
    -0.08
    orne
    -0.08
    å¹´åįİ
    -0.07
    miny
    -0.07
    лей
    -0.07
    าศ
    -0.07
    ominated
    -0.07
    æį¢æĿ¥çļĦ
    -0.07
    orida
    -0.07
    æį¢æĿ¥
    -0.07
    POSITIVE LOGITS
     intermedi
    0.08
    eren
    0.08
    æĽ´åħ¨
    0.08
     intermediate
    0.07
    åĨľæĿijåľ°åĮº
    0.07
    积累äºĨ丰å¯ĮçļĦ
    0.07
     пÑĢомежÑĥ
    0.07
    ary
    0.07
    Forms
    0.07
    letcher
    0.07
    Activations Density 0.005%

    No Known Activations