© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 1282
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     *)((
    -0.26
    .Logf
    -0.23
    adays
    -0.22
    |array
    -0.22
    ^K
    -0.22
    ünk
    -0.21
    du
    -0.21
    åĴĮ
    -0.21
    :convert
    -0.21
    /lg
    -0.21
    POSITIVE LOGITS
    trecht
    0.26
    ãģ§ãģĹãĤĩãģĨãģŃ
    0.24
     withRouter
    0.21
    SingleOrDefault
    0.21
     bindActionCreators
    0.21
    ä¸ĵä¸ļä»İäºĭ
    0.21
     HtmlWebpackPlugin
    0.21
    åݾ
    0.20
    广åijĬæľįåĬ¡
    0.20
    leanor
    0.20
    Activations Density 0.927%

    No Known Activations