© 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. 749
    Prev
    Next
    INDEX
    Explanations

    events and actions

    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
     LENG
    -0.33
    ãİı
    -0.33
    -Trump
    -0.33
    .BASELINE
    -0.31
    /*↵
    -0.31
    ãİŀ
    -0.31
    -alist
    -0.31
    ä¸ŃåĽ½ç½ij游
    -0.30
     (){
    -0.29
    æľīçļĦçݩ家
    -0.29
    POSITIVE LOGITS
     (
    0.32
    æīĢ
    0.28
    æĪĸèĢħ说
    0.28
    æīĢæıIJä¾ĽçļĦ
    0.28
     --
    0.27
    çļĦéĤ£ä¸Ģ
    0.26
    以åıĬ
    0.26
    çļĦéĤ£ç§į
    0.26
    èĥ½å¤Łè®©
    0.25
    çļĦä¸Ģç§į
    0.25
    Activations Density 17.658%

    No Known Activations