© 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. 739
    Prev
    Next
    INDEX
    Explanations

    your/yourself

    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
    çļĦ带é¢Ĩ
    -0.32
    berra
    -0.31
    ä¸įèī¯ä¿¡æģ¯
    -0.30
     Playoff
    -0.28
    åĵĪåĵĪåĵĪåĵĪ
    -0.28
     rematch
    -0.27
    èĦ±é¢ĸ
    -0.27
     blowjob
    -0.27
    ä¸Ģ个èģĮä¸ļ
    -0.27
    éĵ©
    -0.26
    POSITIVE LOGITS
     your
    0.60
    your
    0.49
    ä½łçļĦ
    0.44
    æĺ¯ä½ł
    0.41
     you
    0.39
    æĤ¨çļĦ
    0.37
     yourself
    0.36
     Your
    0.36
    Your
    0.36
     YOUR
    0.33
    Activations Density 8.495%

    No Known Activations