© 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. 13184
    Prev
    Next
    INDEX
    Explanations

    UI elements like ListView, Cell, UITableView, UICollectionView

    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
    -0.07
     onDataChange
    -0.06
     trace
    -0.06
    .documentElement
    -0.06
     notation
    -0.06
    trace
    -0.06
    ikes
    -0.06
     household
    -0.06
     Powers
    -0.06
    AllWindows
    -0.06
    POSITIVE LOGITS
    acol
    0.09
    å±ħä¸Ń
    0.09
    å±ħ
    0.09
    æł·å¼ı
    0.09
    IDGET
    0.09
     customize
    0.08
    rech
    0.08
     показа
    0.08
    尺寸
    0.08
     decoration
    0.08
    Activations Density 1.347%

    No Known Activations