© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 36
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    :maj
    -0.25
    retorno
    -0.23
    quartered
    -0.23
    !important
    -0.22
    iếu
    -0.22
     ++)↵
    -0.21
    .scalajs
    -0.21
    .sax
    -0.21
     Filme
    -0.21
    æĥĿ
    -0.20
    POSITIVE LOGITS
     atof
    0.21
     realloc
    0.21
     migliori
    0.20
    ertiary
    0.20
     Executors
    0.20
    :');↵
    0.20
     HOWEVER
    0.20
     rowCount
    0.20
     totalPages
    0.19
    épo
    0.19
    Activations Density 0.748%

    No Known Activations