© 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. 519
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    åħ«å¤§ä»¥æĿ¥
    -0.31
    äºĮåįģå¹´
    -0.27
     Sevent
    -0.26
    _pdu
    -0.25
    ä¹Ŀåįģ
    -0.24
     atIndex
    -0.23
    ä¸ĥå¹´
    -0.23
     ninety
    -0.23
    éķ¿è¾¾
    -0.22
    ä¸īåįģå¹´
    -0.22
    POSITIVE LOGITS
     two
    0.53
     four
    0.52
     three
    0.52
     five
    0.46
     six
    0.43
     several
    0.39
     fewer
    0.36
     seven
    0.36
     eight
    0.36
    åĽĽä¸ª
    0.36
    Activations Density 3.795%

    No Known Activations