© 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. 927
    Prev
    Next
    INDEX
    Explanations

    domain extensions

    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
    @student
    -0.26
    .heroku
    -0.24
    .liferay
    -0.24
    zept
    -0.23
    .gdx
    -0.23
    æĺŁå·´
    -0.21
    .yy
    -0.20
    ----</
    -0.20
    æľ¬æĬ¥
    -0.20
     offsetof
    -0.20
    POSITIVE LOGITS
    .com
    0.42
    .org
    0.37
     com
    0.32
    com
    0.25
    为æĬĵ
    0.24
    classCallCheck
    0.24
    efeller
    0.23
    xbf
    0.23
    .gov
    0.23
    .edu
    0.23
    Activations Density 0.727%

    No Known Activations