© 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. 27646
    Prev
    Next
    INDEX
    Explanations

    Research Report

    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
    è´±
    -0.07
    лок
    -0.07
    xe
    -0.06
    è°ģçŁ¥éģĵ
    -0.06
    çĻ»éĮ²
    -0.06
    çłĶ究äºĨ
    -0.06
    áĥª
    -0.06
     Tutt
    -0.06
    gon
    -0.06
    ydd
    -0.06
    POSITIVE LOGITS
    hod
    0.07
    RootElement
    0.07
    {return
    0.07
    buster
    0.07
    ä¹ĭ为
    0.07
    æĪIJç«ł
    0.07
    ickl
    0.07
    unset
    0.07
    çĥĪ
    0.07
    éĻ¢åĮº
    0.07
    Activations Density 0.003%

    No Known Activations