© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3837
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    /gif
    -0.23
    åľ¨è¿ĩ渡
    -0.22
     tri
    -0.20
    箪
    -0.20
    LES
    -0.20
     положиÑĤелÑĮн
    -0.19
    pile
    -0.19
    /bower
    -0.19
    kont
    -0.19
    .beginTransaction
    -0.18
    POSITIVE LOGITS
    Dlg
    0.21
    orneys
    0.21
    zeit
    0.20
    (Blueprint
    0.20
    orney
    0.20
    tribution
    0.19
    .ManyToMany
    0.19
    ylvania
    0.18
    .Xaml
    0.18
    .GridView
    0.18
    Activations Density 0.001%

    No Known Activations