© 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. 1508
    Prev
    Next
    INDEX
    Explanations

    broad concepts

    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
    /Dk
    -0.27
    -Trump
    -0.26
     Nº
    -0.24
    ".↵↵↵↵
    -0.24
     libertin
    -0.24
    pson
    -0.24
     Playoff
    -0.24
    ?"↵↵↵↵
    -0.24
    byn
    -0.23
     honda
    -0.22
    POSITIVE LOGITS
     society
    0.32
     overall
    0.30
     system
    0.28
    æķ´ä¸ª
    0.28
     total
    0.28
     history
    0.27
     spectrum
    0.26
     our
    0.26
     life
    0.25
    æķ´ä½ĵ
    0.25
    Activations Density 4.273%

    No Known Activations