© 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. 85
    Prev
    Next
    INDEX
    Explanations

    may

    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
     basically
    -0.28
    èĤ¯å®ļ
    -0.27
     usually
    -0.25
    éĢļ常
    -0.25
     probably
    -0.25
    åĩłä¹İ
    -0.24
    éĢļ常æĺ¯
    -0.24
     essentially
    -0.24
     presumably
    -0.24
    تظ
    -0.23
    POSITIVE LOGITS
    ä¹Łåı¯èĥ½
    0.34
     someday
    0.31
    æŁIJ个
    0.23
    èĪ´
    0.22
     algún
    0.22
    ä¹Łæľīä¸ĢäºĽ
    0.22
    ä½ıæĪ¿åħ¬ç§¯
    0.22
    onna
    0.22
    :init
    0.22
     Ä°zmir
    0.21
    Activations Density 1.662%

    No Known Activations