© 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. 1159
    Prev
    Next
    INDEX
    Explanations

    context or manner

    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
    åľ¨åIJĮä¸Ģ
    -0.29
    åľ¨
    -0.29
    åľ¨æķ´ä¸ª
    -0.29
    åľ¨æĪijåĽ½
    -0.27
    åľ¨éĩĮéĿ¢
    -0.27
    åľ¨æѤ
    -0.26
    åľ¨çĶŁæ´»ä¸Ń
    -0.26
    åľ¨è¿ĻéĩĮ
    -0.25
    åľ¨ä¸Ĭæµ·
    -0.25
    åľ¨åĮĹ京
    -0.25
    POSITIVE LOGITS
     manner
    0.43
     guise
    0.39
     context
    0.38
     fashion
    0.34
    çļĦæĥħåĨµä¸ĭ
    0.32
     contexts
    0.31
     ÙĪÙģÙĬ
    0.30
    çļĦåŁºç¡Ģä¸Ĭ
    0.29
     nutshell
    0.28
    çݯå¢ĥä¸Ń
    0.28
    Activations Density 4.627%

    No Known Activations