© 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. 46295
    Prev
    Next
    INDEX
    Explanations

    numbers and time

    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
     Escorts
    -0.28
    ">ÃĹ</
    -0.25
    âĨ¦
    -0.25
     ilma
    -0.25
     Millenn
    -0.24
     GOODS
    -0.23
     danske
    -0.23
     POLIT
    -0.23
    gages
    -0.22
     setBackgroundImage
    -0.22
    POSITIVE LOGITS
    :Event
    0.24
    æį¢åı¥è¯Ŀ
    0.23
    __':č↵
    0.21
    女æĺŁ
    0.20
    .coords
    0.20
    азвание
    0.20
     T
    0.19
     Na
    0.19
    _unsigned
    0.19
    æĬ¡
    0.19
    Activations Density 0.462%

    No Known Activations