© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4017
    Prev
    Next
    INDEX
    Explanations

    Time references

    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
    两个æľĪ
    -0.32
    åįĬå¹´
    -0.30
     Months
    -0.29
    Months
    -0.29
     months
    -0.28
    ä¸ī个æľĪ
    -0.28
    months
    -0.25
    ç§ĭåĨ¬
    -0.24
    åĩłä¸ªæľĪ
    -0.24
    ä¸Ģå¹´å¤ļ
    -0.24
    POSITIVE LOGITS
     today
    0.65
    ä»Ĭ天
    0.59
     tonight
    0.59
     yesterday
    0.59
    ä»Ĭ天çļĦ
    0.57
    ä»ĬæĹ¥
    0.53
    æĺ¨å¤©
    0.50
    Today
    0.50
     Today
    0.50
    today
    0.48
    Activations Density 1.004%

    No Known Activations