© 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. 2946
    Prev
    Next
    INDEX
    Explanations

    meaning

    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
    rysler
    -0.21
    preci
    -0.20
    (and
    -0.20
    ฬ
    -0.20
    —and
    -0.19
    idious
    -0.19
    nish
    -0.19
    scrição
    -0.19
    .IsSuccess
    -0.19
    écoute
    -0.18
    POSITIVE LOGITS
    åį³
    0.82
    ä¹Łå°±æĺ¯è¯´
    0.72
    ä¹Łå°±æĺ¯
    0.70
     meaning
    0.68
     Meaning
    0.65
     ie
    0.60
    meaning
    0.60
    æĦıæĢĿæĺ¯
    0.59
    ãģ¤ãģ¾ãĤĬ
    0.54
    åį³æĺ¯
    0.50
    Activations Density 1.178%

    No Known Activations