© 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. 46238
    Prev
    Next
    INDEX
    Explanations

    why or what

    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
    çļĦ带é¢Ĩ
    -0.26
     ×Ķ×ķ×ĵ
    -0.25
    ynet
    -0.24
    âĨĻ
    -0.23
    .Atomic
    -0.22
     pushViewController
    -0.22
     Ủ
    -0.22
    ISC
    -0.22
    CRET
    -0.22
    âĸ¹
    -0.21
    POSITIVE LOGITS
    åŁºæľ¬
    0.34
     basic
    0.28
    çļĦåŁºæľ¬
    0.26
    è¿Ļå°±æĺ¯
    0.25
    basic
    0.22
     basics
    0.22
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.22
    Basic
    0.22
     pretty
    0.21
    大èĩ´
    0.21
    Activations Density 0.008%

    No Known Activations