© 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. 46184
    Prev
    Next
    INDEX
    Explanations

    examples and ideas

    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
    USART
    -0.22
    ä½£
    -0.20
    пÑĥбли
    -0.20
    unger
    -0.19
    LOCKS
    -0.19
    irie
    -0.19
    tÃŃ
    -0.19
    ----↵
    -0.18
    æĭĶ
    -0.18
     Sponsored
    -0.18
    POSITIVE LOGITS
     lucr
    0.27
    å§Ķç»Ħç»ĩ
    0.23
    cope
    0.21
    ".↵↵↵↵
    0.20
     veter
    0.20
    è§ģæķĪ
    0.19
    mos
    0.19
    ITED
    0.18
     )↵↵↵↵↵↵↵↵
    0.18
    諮詢
    0.18
    Activations Density 0.002%

    No Known Activations