© 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. 599
    Prev
    Next
    INDEX
    Explanations

    been

    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
     currently
    -0.22
    ç«ĭ马
    -0.21
    ordinates
    -0.21
    currently
    -0.21
     immediately
    -0.21
    马ä¸Ĭ
    -0.21
    .badlogic
    -0.20
    æīĢæīĢ
    -0.20
    ä¸Ģä¸ĭ
    -0.20
    ä¸ī大éĺ¶æ®µ
    -0.20
    POSITIVE LOGITS
     lately
    0.49
     since
    0.44
    since
    0.39
    以æĿ¥
    0.38
     recently
    0.35
    æľĪ以æĿ¥
    0.34
    Since
    0.34
    å¤ļ次
    0.34
     been
    0.32
    _since
    0.32
    Activations Density 2.507%

    No Known Activations