© 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. 1082
    Prev
    Next
    INDEX
    Explanations

    software distribution

    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
    "class
    -0.25
     dealloc
    -0.23
    -ajax
    -0.23
    .charCodeAt
    -0.23
    åĪĨæł¡
    -0.22
    itere
    -0.22
    ByUrl
    -0.22
    .'/'.$
    -0.21
    -gnu
    -0.21
    setSize
    -0.21
    POSITIVE LOGITS
    /Dk
    0.30
    /stretch
    0.29
    Türkiye
    0.27
     оÑĤмеÑĤил
    0.24
    âĮĤ
    0.23
     заÑıвил
    0.23
    å¦Ĺ
    0.22
     ${({
    0.21
    个交æĺĵ
    0.21
    ,strlen
    0.21
    Activations Density 3.857%

    No Known Activations