© 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. 45910
    Prev
    Next
    INDEX
    Explanations

    food ingredients

    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
    "<?
    -0.23
    conexao
    -0.22
    das
    -0.21
    mium
    -0.21
    suming
    -0.20
    ç³»
    -0.20
    æµģæ°´
    -0.19
    %");↵
    -0.19
    ;');↵
    -0.19
    orsk
    -0.19
    POSITIVE LOGITS
    éĢīèĤ¡
    0.25
    Calibri
    0.22
    imore
    0.20
     licensors
    0.20
    eroon
    0.20
    ´Ī
    0.19
     sluts
    0.19
    )((((
    0.19
    æľĭåıĭ们对
    0.19
    kok
    0.19
    Activations Density 0.050%

    No Known Activations