© 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. 2300
    Prev
    Next
    INDEX
    Explanations

    Code or technical fragments

    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
    _combine
    -0.20
    çĺ¾
    -0.19
    OURCE
    -0.19
    ãĤ½
    -0.19
     pragma
    -0.18
     nouve
    -0.18
    ather
    -0.18
    èµĦæºIJæķ´åIJĪ
    -0.18
     tablesp
    -0.18
    à¹Į
    -0.18
    POSITIVE LOGITS
    æĸĽ
    0.23
    iltr
    0.22
    pressão
    0.22
    nqu
    0.21
    vê
    0.21
    ornings
    0.20
    полнение
    0.20
    ILLISECONDS
    0.20
     bindActionCreators
    0.20
     ?>↵↵↵
    0.19
    Activations Density 0.001%

    No Known Activations