© 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. 1378
    Prev
    Next
    INDEX
    Explanations

    addition

    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
     sublic
    -0.24
    getJSON
    -0.22
    setw
    -0.21
    wner
    -0.20
    ceptar
    -0.20
     {?>↵
    -0.20
    rão
    -0.19
    èħł
    -0.19
    InMillis
    -0.19
    rire
    -0.19
    POSITIVE LOGITS
     added
    0.60
    æ·»åĬł
    0.52
    added
    0.51
     addition
    0.51
    é¢Ŀå¤ĸ
    0.48
     additional
    0.48
     Added
    0.47
     thêm
    0.47
     æ·»åĬł
    0.47
    Added
    0.47
    Activations Density 5.640%

    No Known Activations