© 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. 1122
    Prev
    Next
    INDEX
    Explanations

    time event during

    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
     èĩªåĬ¨çĶŁæĪIJ
    -0.41
    -scenes
    -0.40
     maneu
    -0.34
     Annunci
    -0.33
    /Gate
    -0.30
    /stretch
    -0.29
    :invoke
    -0.29
     annunci
    -0.28
     çĶŁåij½åij¨æľŁ
    -0.27
    Intialized
    -0.26
    POSITIVE LOGITS
    notated
    0.27
     event
    0.26
    æľŁéĹ´
    0.26
     time
    0.25
     wait
    0.25
    称ä¹ĭ
    0.24
     deltaTime
    0.24
    äºĭ件
    0.24
     during
    0.24
     gridColumn
    0.23
    Activations Density 3.904%

    No Known Activations