© 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. 70
    Prev
    Next
    INDEX
    Explanations

    file storage

    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
    åºĶæĶ¶è´¦
    -0.29
    对åħ¶çľŁå®ŀ
    -0.28
     NotSupportedException
    -0.28
    /Dk
    -0.24
    ÎIJ
    -0.23
    ãİİ
    -0.23
     AudioSource
    -0.23
     FactoryBot
    -0.22
    izoph
    -0.22
     OnCollision
    -0.21
    POSITIVE LOGITS
    åŃĺåĤ¨
    0.37
     storage
    0.35
    ä¿ĿåŃĺ
    0.35
     file
    0.31
     data
    0.31
     contents
    0.30
     stored
    0.30
    åĤ¨åŃĺ
    0.29
    ä¿Ŀ管
    0.28
    data
    0.28
    Activations Density 6.657%

    No Known Activations