© 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. 1311
    Prev
    Next
    INDEX
    Explanations

    military operations

    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
     imageData
    -0.25
    éĢīèĤ¡
    -0.25
    ä¸ī大èģĮä¸ļ
    -0.25
    èµ°åĬ¿åĽ¾
    -0.25
     assail
    -0.24
    ä¸īç§įèģĮä¸ļ
    -0.24
    Brightness
    -0.24
    æĪĺ士èģĮä¸ļ
    -0.23
    çĤ¸å¼¹
    -0.23
    æ³ķå¸ĪèģĮä¸ļ
    -0.23
    POSITIVE LOGITS
     matchups
    0.34
     Playoff
    0.29
    åĨ°æ·ĩ
    0.28
    berra
    0.28
    æĢ§ä»·
    0.27
     roma
    0.26
     Melania
    0.25
    Deployment
    0.25
     bufsize
    0.25
     deployments
    0.25
    Activations Density 2.637%

    No Known Activations