© 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. 977
    Prev
    Next
    INDEX
    Explanations

    samples

    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
    âĸ¿
    -0.24
     Jerseys
    -0.23
     Subaru
    -0.21
     (*((
    -0.21
    åĺīå¹´
    -0.21
    ()=>{↵
    -0.21
     metic
    -0.20
    cej
    -0.20
     redistributed
    -0.20
     McCart
    -0.20
    POSITIVE LOGITS
     samples
    0.38
    æł·æľ¬
    0.36
     sample
    0.35
    对çħ§
    0.32
    æł·åĵģ
    0.28
     healthy
    0.28
     Samples
    0.28
    sample
    0.27
     comparison
    0.27
     Sample
    0.26
    Activations Density 4.258%

    No Known Activations