© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 10
    Prev
    Next
    INDEX
    Explanations

    increasing popularity

    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
    =admin
    -0.28
    çļĦ带é¢Ĩ
    -0.28
     staffers
    -0.27
    è¹ļ
    -0.27
    åį®
    -0.26
    åı¯ä»¥æĽ´å¥½
    -0.26
    çŀŁ
    -0.26
    stÄĻp
    -0.25
    å±Ĥåĩº
    -0.24
    imagenes
    -0.24
    POSITIVE LOGITS
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.38
     increasingly
    0.37
     trend
    0.34
     trends
    0.32
    è¶ĬæĿ¥è¶Ĭ
    0.32
    è¶ĭåĬ¿
    0.31
    æľīæľŁå¾Ĵ
    0.30
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    0.29
     lately
    0.29
     popularity
    0.28
    Activations Density 8.122%

    No Known Activations