© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3547
    Prev
    Next
    INDEX
    Explanations

    main function

    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
    åĴ¤
    -0.19
    æł¸çĶµ
    -0.19
    .contentMode
    -0.19
    åħ¶å®ĥéĹ®é¢ĺ
    -0.18
    .mockito
    -0.18
    éķ¿æľŁ
    -0.18
    æīĭç»Ńè´¹
    -0.18
     Spy
    -0.18
    _library
    -0.17
    @property
    -0.17
    POSITIVE LOGITS
     main
    0.35
    main
    0.32
     Main
    0.30
    .Main
    0.29
    argc
    0.28
    /Dk
    0.28
    MAIN
    0.27
    .main
    0.27
    (argc
    0.27
     MAIN
    0.25
    Activations Density 0.470%

    No Known Activations