© 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. 1490
    Prev
    Next
    INDEX
    Explanations

    COVID, https, Biden, emoji

    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
    游æĪı代
    -0.33
    âĦł
    -0.30
     iPod
    -0.29
    å¿ĥå¾Ĺä½ĵä¼ļ
    -0.28
    åįģäºĮäºĶ
    -0.28
    âľĹ
    -0.28
    ä¸įèī¯ä¿¡æģ¯
    -0.28
    æ±Ĩ
    -0.27
    âĺº
    -0.27
    好象
    -0.27
    POSITIVE LOGITS
     ðŁ
    0.47
     ðŁij
    0.39
     https
    0.39
    https
    0.36
     ðŁĴ
    0.35
    èµĭèĥ½
    0.35
     COVID
    0.34
    COVID
    0.34
     Biden
    0.34
     emoji
    0.34
    Activations Density 23.670%

    No Known Activations