© 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. 1095
    Prev
    Next
    INDEX
    Explanations

    say "let" or "what"

    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
    âļĹ
    -0.26
    ðŁĵIJ
    -0.26
    伧
    -0.23
    ÐŁÐ¾Ð´ÑĢобнее
    -0.23
    [sizeof
    -0.22
    orado
    -0.22
    nodiscard
    -0.21
    nek
    -0.21
    ðŁĻĭ
    -0.21
    _saida
    -0.21
    POSITIVE LOGITS
     imageURL
    0.26
    æĢ»èĢĮè¨Ģä¹ĭ
    0.25
    æį¢åı¥è¯Ŀ
    0.24
    æľīæĦıæĢĿçļĦ
    0.22
     اÙĦساد
    0.22
    æĢİä¹Īåı¯èĥ½
    0.21
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.21
    æĢİä¹Īèĥ½
    0.21
    è¿ĺæľīä»Ģä¹Ī
    0.20
    åĩŃä»Ģä¹Ī
    0.20
    Activations Density 0.094%

    No Known Activations