© 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. 635
    Prev
    Next
    INDEX
    Explanations

    technical and computational terms

    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
     dames
    -0.25
    ={"/
    -0.24
    '].'/
    -0.24
     sucht
    -0.23
    ^K
    -0.22
    çħ
    -0.22
    ;/*
    -0.21
    æĦİ
    -0.21
     )[
    -0.21
    &&!
    -0.21
    POSITIVE LOGITS
     CircularProgress
    0.32
    åħ¨åĬĽä»¥
    0.29
    äºĨ好åĩł
    0.25
     modalitÃł
    0.24
    çĸĶ
    0.24
    纰
    0.24
     ningu
    0.23
    woke
    0.23
    scribe
    0.23
    CompleteListener
    0.23
    Activations Density 0.659%

    No Known Activations