© 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. 1270
    Prev
    Next
    INDEX
    Explanations

    medical and scientific

    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
     scaleY
    -0.30
    conexao
    -0.23
     sublicense
    -0.22
     licensors
    -0.22
    Uvs
    -0.22
    ItemImage
    -0.21
    :Array
    -0.21
    èĸ¨
    -0.21
    ToPoint
    -0.21
    setImage
    -0.20
    POSITIVE LOGITS
    æģ¯æģ¯
    0.29
    /Private
    0.29
    è°¢è°¢ä½ł
    0.25
    以人æ°ij为
    0.25
    æĪĸå¤ļ
    0.24
    ASHINGTON
    0.23
    ,},↵
    0.23
     (~(
    0.23
    æĢ§ä»·
    0.23
    /native
    0.22
    Activations Density 8.615%

    No Known Activations