© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1405
    Prev
    Next
    INDEX
    Explanations

    scientific abbreviations

    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
     airstrikes
    -0.24
    è¿Ļ个èģĮä¸ļ
    -0.23
    çļĦ带é¢Ĩ
    -0.22
    æĤ¨åIJĮæĦı
    -0.22
    (){}↵↵
    -0.22
    ä¸Ģ个èģĮä¸ļ
    -0.21
     generado
    -0.21
     RaisePropertyChanged
    -0.20
    .checkNotNull
    -0.20
    (){}↵
    -0.19
    POSITIVE LOGITS
    indsight
    0.30
    ledged
    0.28
    ].'
    0.26
    /Dk
    0.25
    errals
    0.24
    ensibly
    0.24
    astered
    0.24
    readcr
    0.23
    acle
    0.23
    estroy
    0.23
    Activations Density 0.006%

    No Known Activations