© 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. 677
    Prev
    Next
    INDEX
    Explanations

    release notes reports

    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
    RouterModule
    -0.26
    ì°®
    -0.26
    Sharper
    -0.25
    ".↵↵↵↵
    -0.25
    ;background
    -0.23
    quartered
    -0.23
    :black
    -0.23
    qus
    -0.23
    /Dk
    -0.23
    åĨ°æ·ĩ
    -0.23
    POSITIVE LOGITS
    à¸īà¸ļ
    0.35
     containing
    0.33
     contain
    0.32
     contains
    0.31
    _contains
    0.29
    åī¯æľ¬
    0.28
    åĨħ容
    0.27
    contains
    0.27
     contents
    0.27
     dated
    0.26
    Activations Density 4.127%

    No Known Activations