© 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. 1219
    Prev
    Next
    INDEX
    Explanations

    code or garbage

    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
    berra
    -0.21
     PureComponent
    -0.21
    itmap
    -0.20
    edom
    -0.20
    ieties
    -0.20
    coma
    -0.20
    NullOrEmpty
    -0.20
    rides
    -0.19
    iswa
    -0.19
    raphics
    -0.19
    POSITIVE LOGITS
    æľĭåıĭ们对
    0.22
    /vendors
    0.21
    ($('.
    0.21
    âĨĻ
    0.20
    <header
    0.20
    éļĨéĩį举è¡Į
    0.20
    łí
    0.20
     velit
    0.19
    إسÙĦاÙħ
    0.19
    ä¸ĩä½Ļ
    0.19
    Activations Density 1.805%

    No Known Activations