© 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. 1945
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    YPES
    -0.25
    apolis
    -0.21
     addObserver
    -0.20
    /cop
    -0.20
    herits
    -0.20
    embros
    -0.20
    DATES
    -0.19
    acades
    -0.18
     înt
    -0.18
    æĭ±
    -0.18
    POSITIVE LOGITS
    /+
    0.26
    mozilla
    0.23
    intégr
    0.21
    åĽ½éĻħåľ¨çº¿
    0.21
    spa
    0.21
    {Name
    0.20
    =-
    0.20
    ä¸ĭæĿ¥
    0.20
    ä¹ľ
    0.20
    åĬłæ·±
    0.20
    Activations Density 0.863%

    No Known Activations