© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 46244
    Prev
    Next
    INDEX
    Explanations

    AI system prompts

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .puts
    -0.23
    è¹ģ
    -0.21
    å±Ĥåĩº
    -0.20
    :ss
    -0.20
    |--------------------------------------------------------------------------↵
    -0.19
    lz
    -0.19
     !=↵
    -0.19
    ç½ijç«Ļé¦ĸ页
    -0.19
    说æĺ¯
    -0.19
    èľĵ
    -0.19
    POSITIVE LOGITS
     HuffPost
    0.25
     BuzzFeed
    0.23
    estroy
    0.21
    elsea
    0.21
    ++){↵↵
    0.20
    Began
    0.20
    ystems
    0.19
    icers
    0.19
     )↵↵↵↵↵↵↵↵
    0.18
    wiÄĻ
    0.18
    Activations Density 0.003%

    No Known Activations