© 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. 191
    Prev
    Next
    INDEX
    Explanations

    work, job, employees

    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
    主èIJ¥ä¸ļ
    -0.27
    ç¡ķ士çłĶ究
    -0.26
     anv
    -0.24
     QPixmap
    -0.23
    .OrderByDescending
    -0.23
     panties
    -0.23
     NDEBUG
    -0.23
     QImage
    -0.22
    èĪ¯
    -0.22
    åħ¨åĬĽä»¥
    -0.21
    POSITIVE LOGITS
    å²Ĺä½į
    0.40
    å²Ĺ
    0.36
    å·¥ä½ľ
    0.36
     work
    0.35
    å·¥ä½ľå²Ĺä½į
    0.33
     job
    0.32
    å·¥ä½ľä»»åĬ¡
    0.30
     duties
    0.30
    çļĦå·¥ä½ľ
    0.29
    å·¥ä½ľçļĦ
    0.29
    Activations Density 3.427%

    No Known Activations