© 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. 471
    Prev
    Next
    INDEX
    Explanations

    code or web

    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
    emoji
    -0.31
     emoji
    -0.30
    ıc
    -0.29
    ç²¾åĩĨ
    -0.29
    }elseif
    -0.28
     https
    -0.28
    ï¸ı
    -0.27
     ðŁ
    -0.27
     emojis
    -0.27
    nullptr
    -0.26
    POSITIVE LOGITS
    好象
    0.33
    -scalable
    0.31
    .htm
    0.30
    å¿ĥå¾Ĺä½ĵä¼ļ
    0.28
    æ±Ĩ
    0.26
     bogus
    0.26
    游æĪı代
    0.26
     daÃŁ
    0.24
    âĦł
    0.24
    /cgi
    0.24
    Activations Density 4.585%

    No Known Activations