© 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. 18002
    Prev
    Next
    INDEX
    Explanations

    titles and beginnings of code/scripts

    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
    ÙģاÙģ
    -0.07
     scrim
    -0.07
    athom
    -0.07
    åī©
    -0.07
    pheres
    -0.07
     estip
    -0.07
    åĪĨä¹ĭ
    -0.07
    uron
    -0.07
    é»Ħé¾Ļ
    -0.07
    .Details
    -0.07
    POSITIVE LOGITS
     title
    0.08
    title
    0.08
    大家好
    0.08
    Welcome
    0.08
    æłĩé¢ĺ
    0.08
    欢è¿İæĿ¥åĪ°
    0.08
     Welcome
    0.07
    =title
    0.07
    æĤ¨å¥½
    0.07
     Title
    0.07
    Activations Density 1.654%

    No Known Activations