© 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. 13147
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
    ç¼
    -0.07
     âĢŀ
    -0.06
     ↵
    -0.06
     unknown
    -0.06
    el
    -0.06
     ...
    -0.06
    L
    -0.06
    inkle
    -0.05
     um
    -0.05
    ½
    -0.05
    POSITIVE LOGITS
    arda
    0.09
    åİĮ
    0.08
    uai
    0.08
    oley
    0.08
    à¸Ĺะ
    0.08
    kea
    0.08
    æ±²
    0.08
    षà¥įà¤ł
    0.08
    hift
    0.08
     boto
    0.08
    Activations Density 0.689%

    No Known Activations