© 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. 652
    Prev
    Next
    INDEX
    Explanations

    How

    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
    ;o
    -0.24
    âĸ»
    -0.22
    ðŁĶ¼
    -0.21
    ----</
    -0.21
    /security
    -0.21
     earthqu
    -0.21
    ÅIJ
    -0.21
    udeau
    -0.20
    endencies
    -0.20
    +");↵
    -0.20
    POSITIVE LOGITS
     How
    0.31
    How
    0.29
     how
    0.27
    åħ³äºİ
    0.27
    å¦Ĥä½ķ
    0.26
    how
    0.25
    åħ³äºİæĪij们
    0.25
    ﹤
    0.24
    çķĮ第ä¸Ģ
    0.24
    æīĢæīĢ
    0.23
    Activations Density 2.433%

    No Known Activations