© 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. 903
    Prev
    Next
    INDEX
    Explanations

    Microsoft

    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
    //↵↵↵
    -0.20
    HLT
    -0.20
    åĮħåŃIJ
    -0.20
    \TestCase
    -0.19
    USART
    -0.19
    .openConnection
    -0.19
    .epam
    -0.19
     actionTypes
    -0.19
    igator
    -0.18
    æīİ
    -0.18
    POSITIVE LOGITS
    Microsoft
    0.40
    .microsoft
    0.39
     Microsoft
    0.36
    微软
    0.33
     microsoft
    0.32
    azure
    0.29
    Michigan
    0.24
    Azure
    0.24
    dbo
    0.23
    alborg
    0.23
    Activations Density 3.903%

    No Known Activations