© 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. 1411
    Prev
    Next
    INDEX
    Explanations

    Chinese 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
    /Dk
    -0.30
    -scalable
    -0.28
    æį¢åı¥è¯Ŀ
    -0.28
     '",
    -0.27
     francais
    -0.27
     newcom
    -0.27
    ï¼ģï¼ģ↵↵
    -0.26
    ););↵
    -0.26
    ãĢĤ↵↵↵↵
    -0.25
    MatrixXd
    -0.25
    POSITIVE LOGITS
    åħļæĢ»
    0.44
    çıŃåŃIJæĪIJåijĺ
    0.34
    åħļæĢ»æĶ¯
    0.34
    纪å§Ķ书记
    0.30
    åħļé£İ
    0.29
    å§Ķåī¯ä¹¦è®°
    0.28
    åħļå·¥å§Ķ
    0.27
    çİŁ
    0.27
    缸åħ³è´Łè´£
    0.26
    åĪ©çĶ¨æĤ¨çļĦ
    0.26
    Activations Density 53.500%

    No Known Activations