© 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. 1513
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
     fkk
    -0.26
    'options
    -0.22
    massage
    -0.21
    |{↵
    -0.21
    detalle
    -0.20
    ÙĪÙĩا
    -0.20
    çļĦä¸ĢäºĽ
    -0.20
    errorCode
    -0.20
    manın
    -0.20
     ?><
    -0.19
    POSITIVE LOGITS
    :
    0.36
    ä½Ĩä¸įéĻIJäºİ
    0.36
     namely
    0.34
    ï¼ļ
    0.33
    ä¸Ģæĺ¯
    0.33
    nam
    0.31
     “
    0.30
    éĤ£å°±æĺ¯
    0.30
     ‘
    0.28
     "
    0.26
    Activations Density 3.075%

    No Known Activations