© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4184
    Prev
    Next
    INDEX
    Explanations

    swap

    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
    Negative Logits
    ÅĽÄĩ
    -0.25
    ï¼ģ",
    -0.21
    lashes
    -0.21
    åŀ¤
    -0.20
    éĵ©
    -0.20
    -Compatible
    -0.20
    éĢ£ãĤĮ
    -0.20
    âĻ®
    -0.20
    SCII
    -0.20
    schlie
    -0.19
    POSITIVE LOGITS
    交æį¢
    0.54
     swap
    0.48
     Swap
    0.48
     swapped
    0.46
    swap
    0.45
     swaps
    0.44
     swapping
    0.43
    é¢ł
    0.43
    Swap
    0.41
    æį¢
    0.41
    Activations Density 0.098%

    No Known Activations