© 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. 1326
    Prev
    Next
    INDEX
    Explanations

    import

    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
    éĽĨåĽ¢èĤ¡ä»½
    -0.23
    .GetEnumerator
    -0.20
    ToEnd
    -0.20
     aliqua
    -0.20
    iscal
    -0.19
     vard
    -0.19
     slee
    -0.19
    æĭ
    -0.19
     decking
    -0.19
    \
    -0.19
    POSITIVE LOGITS
     IonicPage
    0.27
    游æĪıéĩĮçļĦ
    0.26
    å¾Īå¤ļçݩ家
    0.26
    ä½»
    0.24
    游æĪıæĵįä½ľ
    0.24
     iNdEx
    0.23
    åıĪ好åıĪå¿«
    0.23
    ð¬Ģ©
    0.23
    ä¸Ģèĩ´å¥½è¯Ħ
    0.23
    åıĭæĥħéĵ¾æİ¥
    0.22
    Activations Density 0.606%

    No Known Activations