© 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. 1093
    Prev
    Next
    INDEX
    Explanations

    law and regulation

    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
     èĭ¥è¦ģ
    -0.28
     Erectile
    -0.25
    ä»ħ代表
    -0.23
    翾
    -0.20
     ?>&
    -0.19
    è¿Ľåıĸ
    -0.19
    åijĶ
    -0.19
    ail
    -0.19
     */↵↵↵↵
    -0.19
    asiswa
    -0.19
    POSITIVE LOGITS
    è§Ħå®ļ
    0.30
    å®ŀæĸ½ç»ĨåĪĻ
    0.29
    æĿ¡ä¾ĭ
    0.29
    è§Ħå®ļçļĦ
    0.26
    çļĦè§Ħå®ļ
    0.26
     law
    0.26
    缸åħ³è§Ħå®ļ
    0.26
    islation
    0.24
     Act
    0.24
    è¦ıå®ļ
    0.24
    Activations Density 0.761%

    No Known Activations