© 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. 364
    Prev
    Next
    INDEX
    Explanations

    money and cost

    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
     semiclass
    -0.27
     Bitcoins
    -0.26
    æĸ°æµªè´¢ç»ı
    -0.24
    ä½ıæĪ¿åħ¬ç§¯
    -0.23
    é»ijæģ¶
    -0.23
     '|'
    -0.23
     FactoryGirl
    -0.23
     '&'
    -0.23
     Deadpool
    -0.23
    .parseColor
    -0.23
    POSITIVE LOGITS
     amounts
    0.28
    >tag
    0.27
    ,DB
    0.26
    ;br
    0.26
    æĢ»é¢Ŀ
    0.26
    [];č↵
    0.25
    SSIP
    0.25
     sums
    0.25
    :<?
    0.24
    ','#
    0.24
    Activations Density 2.740%

    No Known Activations