© 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. 611
    Prev
    Next
    INDEX
    Explanations

    awards and winners

    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
    åIJįåĪĹåīį
    -0.34
    åħ¨èµĦåŃIJ
    -0.31
    ä¸įèī¯ä¿¡æģ¯
    -0.24
    åĿļå®ļä¸į
    -0.24
    讹
    -0.24
    DBObject
    -0.23
    _relu
    -0.23
    大约
    -0.23
    éķ¿çº¦
    -0.23
    äºĭåıij
    -0.22
    POSITIVE LOGITS
    年度
    0.26
     record
    0.25
    GLfloat
    0.24
     coveted
    0.23
     recognition
    0.23
    åįķ项
    0.22
    })();↵↵
    0.22
     overall
    0.22
     title
    0.21
    ighest
    0.21
    Activations Density 3.926%

    No Known Activations