© 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. 1453
    Prev
    Next
    INDEX
    Explanations

    `<` symbol

    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
    matchCondition
    -0.29
     bü
    -0.25
    iversary
    -0.24
     IsActive
    -0.24
    printStats
    -0.23
    ATEGORY
    -0.23
    abouts
    -0.23
     Fucking
    -0.23
    влеÑĩен
    -0.23
    ritte
    -0.22
    POSITIVE LOGITS
    serter
    0.31
    EMAIL
    0.28
    åıĸåĨ³
    0.27
    æĢ§ä»·
    0.25
    "value
    0.24
    æĸ°åĬł
    0.23
    ä»İæł¹æľ¬
    0.23
    æŁ¥çľĭ详æĥħ
    0.22
    çķĻè¨ĢæĿ¿
    0.22
    влажн
    0.21
    Activations Density 0.242%

    No Known Activations