© 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. 1887
    Prev
    Next
    INDEX
    Explanations

    .

    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
    à¹Ģà¸ľà¸¢à¹ģà¸ŀร
    -0.23
     and
    -0.22
    webElement
    -0.22
    毫æĹłçĸij
    -0.22
    è¯
    -0.21
    ,
    -0.21
    ï¼ģï¼ģ↵↵
    -0.21
    åľ¨çݩ家
    -0.21
    foundland
    -0.21
     ************************************************
    -0.21
    POSITIVE LOGITS
    -scalable
    0.33
    oriously
    0.30
     cuckold
    0.29
     manh
    0.28
     disappe
    0.28
    -transitional
    0.28
    -expanded
    0.27
     sodom
    0.27
     subparagraph
    0.26
    nesc
    0.26
    Activations Density 11.921%

    No Known Activations