© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 991
    Prev
    Next
    INDEX
    Explanations

    1

    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
    zilla
    -0.23
    	Copyright
    -0.21
     ShoppingCart
    -0.21
     regelmÃ¤ÃŁig
    -0.20
    ingly
    -0.20
    éĤĿ
    -0.20
     metic
    -0.19
    ORIZED
    -0.19
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.19
     ``(
    -0.19
    POSITIVE LOGITS
     ×Ķ×ķ×ĵ
    0.23
    ogenerated
    0.23
    cassert
    0.21
     (![
    0.21
    íŀĻ
    0.20
    thinkable
    0.20
    ponder
    0.20
    nonnull
    0.20
    ScrollIndicator
    0.19
    gency
    0.19
    Activations Density 0.392%

    No Known Activations