© 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-65K
    7. 3158
    Prev
    Next
    INDEX
    Explanations

    specific subjects or entities

    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/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ByPrimaryKey
    -0.21
    .setBackgroundResource
    -0.21
    åŤ
    -0.19
    raud
    -0.19
    æĪĺæĸĹæľº
    -0.18
    åıĪ好åıĪ
    -0.18
    欢è¿İæĤ¨
    -0.18
    åıĪ好
    -0.18
    ../../../../
    -0.18
    æĿ¥çľĭçľĭåIJ§
    -0.18
    POSITIVE LOGITS
    æį¨
    0.24
    ]];↵↵
    0.21
    isoner
    0.20
    contri
    0.20
    incess
    0.20
    cação
    0.20
    emsp
    0.20
    ")));
    0.20
    :disable
    0.20
    usher
    0.20
    Activations Density 0.001%

    No Known Activations