© 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. 46159
    Prev
    Next
    INDEX
    Explanations

    code

    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
    .WriteByte
    -0.22
     next
    -0.21
    disposing
    -0.21
    اÙĦØ·
    -0.21
     Decompiled
    -0.21
    鸡汤
    -0.19
     CActive
    -0.19
    .Ticks
    -0.18
    åħ¨åĽ½
    -0.18
    /bl
    -0.18
    POSITIVE LOGITS
    >:</
    0.24
    .toCharArray
    0.23
    utilus
    0.23
    áIJī
    0.22
    inctions
    0.22
    odyn
    0.22
    pike
    0.22
    :'.$
    0.22
    nü
    0.21
    çĸ³
    0.21
    Activations Density 0.001%

    No Known Activations