© 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. 1377
    Prev
    Next
    INDEX
    Explanations

    shipping and delivery

    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
    ä¸įèī¯ä¿¡æģ¯
    -0.41
     subpo
    -0.34
    é»ijæģ¶
    -0.33
    å¥ĸåѦ
    -0.31
    åºĶæĶ¶è´¦
    -0.31
     Playoff
    -0.29
    个交æĺĵ
    -0.28
     equipments
    -0.27
    åĿļå®ļä¸į
    -0.27
     InvalidArgumentException
    -0.26
    POSITIVE LOGITS
    âļĹ
    0.43
    ðŁĵIJ
    0.41
    âĦħ
    0.38
    âĹĤ
    0.36
     earthqu
    0.34
    ðŁĵĻ
    0.31
    ä¸įçŁ¥ä¸į
    0.29
    尺寸
    0.29
    -UA
    0.29
     maneu
    0.29
    Activations Density 5.972%

    No Known Activations