© 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. 1053
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    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
    ä¹Įåħĭ
    -0.47
    豪车
    -0.40
     maté
    -0.39
    並å°ĩ
    -0.37
    æĸ°éĽ¶åĶ®
    -0.36
    GameManager
    -0.36
     )↵↵↵↵↵↵↵↵
    -0.35
    /Private
    -0.34
    SizePolicy
    -0.34
    å·´åŁº
    -0.34
    POSITIVE LOGITS
    åľ¨çº¿åĴ¨è¯¢
    0.47
    ç½ijé¦ĸ页
    0.47
    çĶ¨å¾®ä¿¡
    0.40
    æŁ¥çľĭ详æĥħ
    0.39
    ÃŃculo
    0.38
    åĭł
    0.38
    女æĢ§æľĭåıĭ
    0.37
     Unsure
    0.37
    ÃŃculos
    0.36
    è¹Ĥ
    0.34
    Activations Density 19.387%

    No Known Activations