© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1273
    Prev
    Next
    INDEX
    Explanations

    people

    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
    noinspection
    -0.26
    AuthProvider
    -0.25
    *******č↵
    -0.25
    /vendors
    -0.25
    mensagem
    -0.24
    .AddScoped
    -0.24
    thinkable
    -0.23
     INCIDENTAL
    -0.23
     onFinish
    -0.23
    _puts
    -0.22
    POSITIVE LOGITS
    çļĦ带é¢Ĩ
    0.40
     people
    0.37
    individual
    0.31
     PEOPLE
    0.30
    ä¸ī大éĺ¶æ®µ
    0.30
    people
    0.29
    ç³Ĺ
    0.28
     dumpsters
    0.28
     individuals
    0.27
    ä¹ĭ人
    0.27
    Activations Density 6.639%

    No Known Activations