© 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. 618
    Prev
    Next
    INDEX
    Explanations

    temporal sequence

    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
    åļĨ
    -0.24
    -scenes
    -0.23
     millenn
    -0.21
     disappe
    -0.21
     awakeFromNib
    -0.21
    .Quad
    -0.21
     presentViewController
    -0.20
     давно
    -0.20
    çļĦç¼ĺæķħ
    -0.20
     beforehand
    -0.20
    POSITIVE LOGITS
    éļıåIJİ
    0.77
    çĦ¶åIJİ
    0.75
     then
    0.73
    æİ¥çĿĢ
    0.71
     subsequently
    0.68
    çĦ¶åIJİåĨį
    0.66
    ä¹ĭåIJİ
    0.65
     thereafter
    0.63
     subsequent
    0.63
    then
    0.61
    Activations Density 6.241%

    No Known Activations