© 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. 754
    Prev
    Next
    INDEX
    Explanations

    state or description

    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
    	Copyright
    -0.27
    irth
    -0.20
    uze
    -0.19
     yıl
    -0.19
    ingham
    -0.19
     suce
    -0.18
    Feels
    -0.18
     bufio
    -0.17
    isk
    -0.17
    EMPL
    -0.17
    POSITIVE LOGITS
    owntown
    0.25
    coholic
    0.22
    scrição
    0.21
    estroy
    0.21
    readcr
    0.21
    {}{↵
    0.21
    (strpos
    0.21
    .ObjectId
    0.21
    кÑĤив
    0.21
    ventus
    0.20
    Activations Density 0.004%

    No Known Activations