© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1482
    Prev
    Next
    INDEX
    Explanations

    future events

    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
    åīįä¸Ģ天
    -0.25
     imageURL
    -0.24
    æľĪ以æĿ¥
    -0.23
    almost
    -0.23
     almost
    -0.23
    sometimes
    -0.23
    æľīæŶ
    -0.22
    Recently
    -0.22
     Almost
    -0.21
     sometimes
    -0.21
    POSITIVE LOGITS
    å±ĬæŶ
    0.62
     future
    0.59
    æľªæĿ¥çļĦ
    0.54
    å°ĨæĿ¥
    0.53
    æľªæĿ¥
    0.52
     tomorrow
    0.51
    ä»ĬåIJİ
    0.49
    åĪ°æŶåĢĻ
    0.49
     someday
    0.48
     next
    0.48
    Activations Density 4.336%

    No Known Activations