© 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. 396
    Prev
    Next
    INDEX
    Explanations

    text fragments

    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
    ERCHANT
    -0.24
    аÑĤегоÑĢ
    -0.22
    ÑģколÑĮко
    -0.21
    ÙĨتÙĩاء
    -0.21
    ysqli
    -0.21
    ooky
    -0.20
    -0.20
    raith
    -0.20
    ribly
    -0.20
    ultipartFile
    -0.20
    POSITIVE LOGITS
    ÙĪضÙĪع
    0.37
    FTER
    0.31
     yans
    0.29
     tats
    0.29
    جÙħÙĪعة
    0.29
    Putin
    0.28
     âĻ¥
    0.28
     jadx
    0.28
    æĸ°æµªè´¢ç»ı
    0.28
     ifdef
    0.27
    Activations Density 8.116%

    No Known Activations