© 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. 22511
    Prev
    Next
    INDEX
    Explanations

    materials and their properties

    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
    西äºŀ
    -0.08
    çĶĺéľ²
    -0.07
    YPD
    -0.07
    erma
    -0.07
    çļĦåħ¨éĥ¨åĨħ容
    -0.07
    ault
    -0.07
    צר
    -0.07
    åľ¨ç¤¾åĮº
    -0.07
    aller
    -0.07
    жиÑĤ
    -0.07
    POSITIVE LOGITS
     undergoing
    0.09
     materials
    0.09
    ä»ĭè´¨
    0.09
    æĿIJæĸĻ
    0.08
    material
    0.08
    materials
    0.08
    æĿIJè´¨
    0.08
    imitives
    0.08
     material
    0.07
    æĿIJæĸĻçļĦ
    0.07
    Activations Density 0.111%

    No Known Activations