© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2017
    Prev
    Next
    INDEX
    Explanations

    you

    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
    éĥ¨åī¯
    -0.29
    ãİŀ
    -0.25
    longleftrightarrow
    -0.23
    Putin
    -0.23
    :numel
    -0.23
    Ymd
    -0.22
    %);↵
    -0.22
    \admin
    -0.21
    åĻĢ
    -0.21
    âĹĤ
    -0.20
    POSITIVE LOGITS
     should
    0.48
     can
    0.45
    åı¯ä»¥
    0.44
    åºĶ该
    0.43
     could
    0.42
    should
    0.42
     must
    0.41
    åı¯ä»¥åľ¨
    0.40
    åı¯ä»¥éĢļè¿ĩ
    0.39
    åºĶå½ĵ
    0.39
    Activations Density 2.796%

    No Known Activations