© 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. 1433
    Prev
    Next
    INDEX
    Explanations

    Java code

    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
    .scalablytyped
    -0.35
    ffield
    -0.29
    .scalajs
    -0.27
    GuidId
    -0.24
    .Zoom
    -0.23
     getUserId
    -0.22
    [,]
    -0.21
     deutschland
    -0.21
    /XMLSchema
    -0.21
    ospace
    -0.21
    POSITIVE LOGITS
     org
    0.27
     javax
    0.26
     java
    0.24
    KNOWN
    0.23
    .java
    0.23
    {@
    0.22
     Swing
    0.21
     //$
    0.21
     com
    0.20
    [href
    0.20
    Activations Density 2.621%

    No Known Activations