© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1834
    Prev
    Next
    INDEX
    Explanations

    economic policy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĿæģĭ
    -0.31
    ä½ıæĪ¿åħ¬ç§¯
    -0.30
    åı¯ä»¥æĽ´å¥½
    -0.26
    æģĭæĥħ
    -0.26
    âĸİ
    -0.25
     postseason
    -0.24
     acompaña
    -0.24
     setBackgroundImage
    -0.24
     november
    -0.24
     TempData
    -0.24
    POSITIVE LOGITS
    ,private
    0.29
    åĪĴç®Ĺ
    0.28
    ancock
    0.28
     economic
    0.28
     GDP
    0.26
    _predicted
    0.26
    leftright
    0.24
    cies
    0.24
    ç»ıæµİ
    0.24
    .sky
    0.24
    Activations Density 3.562%

    No Known Activations