© 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. 1365
    Prev
    Next
    INDEX
    Explanations

    working well

    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
    以人æ°ij为
    -0.28
    åIJįåĪĹåīį
    -0.24
    #ab
    -0.24
    ä¸įæĸ¹ä¾¿
    -0.23
    ä¸įèī¯ä¿¡æģ¯
    -0.22
     MEDIATEK
    -0.21
     earthqu
    -0.21
     идеалÑĮн
    -0.21
     conveniently
    -0.21
     guarante
    -0.20
    POSITIVE LOGITS
     successfully
    0.41
    æĪIJåĬŁ
    0.40
     good
    0.38
    顺åĪ©
    0.37
     successful
    0.37
     satisfactory
    0.36
    满æĦı
    0.36
    æĪIJåĬŁçļĦ
    0.33
    èī¯å¥½
    0.32
    ä¸Ģèĩ´å¥½è¯Ħ
    0.32
    Activations Density 7.891%

    No Known Activations