© 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. 728
    Prev
    Next
    INDEX
    Explanations

    APIs, services, servers

    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
    大佬
    -0.26
     Hwy
    -0.25
    .ReadString
    -0.25
    ..↵↵↵↵
    -0.24
     Farage
    -0.24
     freel
    -0.23
     paramMap
    -0.23
    窸
    -0.23
    Slf
    -0.22
     "---
    -0.22
    POSITIVE LOGITS
     vö
    0.34
     pBuffer
    0.30
     beforeSend
    0.28
     gameTime
    0.28
     gridColumn
    0.27
    æľĭåıĭ们对
    0.27
     LENG
    0.24
     closeButton
    0.24
     service
    0.24
     libertin
    0.23
    Activations Density 4.385%

    No Known Activations