© 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. 2431
    Prev
    Next
    INDEX
    Explanations

    novel new developed

    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
     traditionally
    -0.26
    éĢļ常æĺ¯
    -0.24
     traditional
    -0.24
     famously
    -0.23
    åºĹåĬłçĽŁ
    -0.23
     commonly
    -0.23
     typically
    -0.23
    常è§ģçļĦ
    -0.22
     notoriously
    -0.22
    ä¼łç»ŁçļĦ
    -0.21
    POSITIVE LOGITS
     developed
    0.29
    prototype
    0.27
     prototype
    0.27
    åij½åIJį为
    0.27
     novel
    0.25
     new
    0.25
    æĸ°çļĦ
    0.24
    æĸ°
    0.24
    	Copyright
    0.24
     newly
    0.24
    Activations Density 1.086%

    No Known Activations