© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    electronic devices and metrics

    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
    æĢ§åĴĮ
    -0.28
    管çIJĨåĴĮ
    -0.26
    ometown
    -0.23
    ìĿ´ëĤĺ
    -0.23
    æĬĢæľ¯åĴĮ
    -0.23
    åĴĮ个人
    -0.23
    åĴĮ社ä¼ļ
    -0.22
     Теп
    -0.22
    åĴĮ
    -0.22
    },č↵č↵
    -0.22
    POSITIVE LOGITS
     respectively
    0.54
     alike
    0.50
    åĿĩæľī
    0.40
    éĥ½éĿŀ常
    0.40
    åĿĩ
    0.39
    è¿ĻäºĽéĥ½æĺ¯
    0.38
    éĥ½åı¯ä»¥
    0.38
    çŃī
    0.38
    éĥ½å¾Ī
    0.38
    éĥ½ä¸įæĺ¯
    0.36
    Activations Density 4.462%

    No Known Activations