© 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. 1042
    Prev
    Next
    INDEX
    Explanations

    9

    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
     beÄŁen
    -0.24
    ighb
    -0.23
    edido
    -0.23
    WillAppear
    -0.23
    airo
    -0.23
    emarks
    -0.22
    å´Ľ
    -0.22
    eterangan
    -0.22
     MediaTek
    -0.21
    å°¼äºļ
    -0.20
    POSITIVE LOGITS
     sovere
    0.28
    æľĭåıĭ们对
    0.25
    VERTISE
    0.21
    æĭĽåķĨå¼ķ
    0.21
    XX
    0.21
    xx
    0.21
    ãģįãģ¡ãĤĵ
    0.21
     CONTR
    0.21
     franca
    0.21
    æ¯ıæĹ¥ç»ıæµİ
    0.21
    Activations Density 0.245%

    No Known Activations