© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    say "a" words

    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
    ;left
    -0.27
    =findViewById
    -0.25
    rescia
    -0.23
    ãĥµ
    -0.23
    æ§ĺãĢħ
    -0.23
     getById
    -0.22
     elÅij
    -0.22
    ﹤
    -0.22
    ;display
    -0.22
     perpetr
    -0.21
    POSITIVE LOGITS
     an
    0.85
     a
    0.84
    ä¸Ģ个
    0.64
    ä¸Ģ个å°ı
    0.56
    ä¸Ģ个æĸ°çļĦ
    0.54
     another
    0.54
    	a
    0.53
    an
    0.49
    a
    0.45
    another
    0.45
    Activations Density 9.578%

    No Known Activations