© 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. 64110
    Prev
    Next
    INDEX
    Explanations

    xml version="1.0" encoding="utf-8"?>

    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
     scout
    -0.07
    äºĮæľĪ
    -0.07
    lave
    -0.06
    isNaN
    -0.06
    æľīäºĮ
    -0.06
    Symfony
    -0.06
    stro
    -0.06
     TÃŃn
    -0.06
     Riv
    -0.06
    দà§į
    -0.06
    POSITIVE LOGITS
    aus
    0.07
    auc
    0.07
    åIJįãģ®
    0.07
    åĨ¶
    0.07
    eah
    0.07
     bewer
    0.07
    incid
    0.06
    _ms
    0.06
     Rosenstein
    0.06
    hill
    0.06
    Activations Density 0.012%

    No Known Activations