© 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. 77
    Prev
    Next
    INDEX
    Explanations

    intensifiers

    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
    ä¹Łæľīä¸ĢäºĽ
    -0.35
     somewhat
    -0.35
    æľīä¸ĢäºĽ
    -0.34
    æľīä¸Ģå®ļçļĦ
    -0.34
    çļĦä¸ĢäºĽ
    -0.32
    æľīæīĢ
    -0.32
    äºĨä¸ĢäºĽ
    -0.29
     occasional
    -0.29
     SOME
    -0.28
    åģ¶å°Ķ
    -0.28
    POSITIVE LOGITS
     literally
    0.39
     absolutely
    0.36
     entire
    0.35
    åħ¨éĥ¨
    0.33
    ç»Ŀ对
    0.33
    æīĢæľī
    0.31
     every
    0.31
    .every
    0.31
     everything
    0.31
    ç»Ŀä¸į
    0.28
    Activations Density 12.713%

    No Known Activations