© 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. 46617
    Prev
    Next
    INDEX
    Explanations

    data and analysis

    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
    ,assign
    -0.20
    ">ÃĹ</
    -0.19
    inheritDoc
    -0.19
    olated
    -0.19
     Guerrero
    -0.18
    eday
    -0.18
    ).(
    -0.18
    ðŁijĭ
    -0.18
    蹶
    -0.18
    æ¹®
    -0.17
    POSITIVE LOGITS
    åĻľ
    0.21
     Ernst
    0.20
    acists
    0.20
    é½ģ
    0.19
    leon
    0.18
    odyn
    0.18
    建档ç«ĭ
    0.17
    解æĶ¾
    0.17
    TestFixture
    0.17
    PushButton
    0.17
    Activations Density 0.001%

    No Known Activations