© 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. 409
    Prev
    Next
    INDEX
    Explanations

    education

    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
    ç¡ķ士çłĶ究
    -0.54
    游æĪıæĬĢå·§
    -0.30
     sovere
    -0.28
     tantra
    -0.26
    æĭľå¸ĪåѦ
    -0.26
     Tantra
    -0.26
    çĶ³åįļ
    -0.26
    æĺ³
    -0.25
    ä½ıæĪ¿åħ¬ç§¯
    -0.25
    traî
    -0.25
    POSITIVE LOGITS
     students
    0.29
     student
    0.28
    对åħ¶çľŁå®ŀ
    0.28
     degree
    0.27
     course
    0.27
    ,},↵
    0.27
     courses
    0.24
     program
    0.24
    åѦçĶŁçļĦ
    0.24
     classes
    0.24
    Activations Density 3.555%

    No Known Activations