© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    math and code

    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
     francais
    -0.24
    ожеÑĤ
    -0.23
    æīĢæīĢ
    -0.23
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.22
    ä¸Ńåħ³
    -0.22
    ç½ijç«Ļé¦ĸ页
    -0.21
    åħ¶å®ĥéĹ®é¢ĺ
    -0.21
     Disorder
    -0.21
    çļĦ带é¢Ĩ
    -0.20
    çļĦæŶéĹ´éĩĮ
    -0.20
    POSITIVE LOGITS
    -Headers
    0.28
    lesc
    0.25
    wdx
    0.24
    .gg
    0.24
    elige
    0.23
    utzer
    0.23
    ceased
    0.23
    /Internal
    0.23
    ;');↵
    0.23
    /Table
    0.23
    Activations Density 0.277%

    No Known Activations