© 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. 1418
    Prev
    Next
    INDEX
    Explanations

    ampersand

    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
    å¤įå·¥å¤į
    -0.36
    åĵĪåĵĪåĵĪåĵĪ
    -0.28
    æĤ»
    -0.28
    ãİĿ
    -0.28
    æĤ¨åIJĮæĦı
    -0.27
    èħĨ
    -0.27
    è¸ħ
    -0.27
    ï¼ĥ
    -0.27
    人大常å§Ķ
    -0.27
    æĤ¨çļĦåŃ©åŃIJ
    -0.26
    POSITIVE LOGITS
    amp
    0.40
    ensely
    0.32
    nbsp
    0.28
    achelor
    0.27
    BoundingClientRect
    0.27
    emsp
    0.25
    ãĤĴ缮
    0.25
    /xhtml
    0.24
    0.23
     bureaucr
    0.23
    Activations Density 0.108%

    No Known Activations