© 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. 1722
    Prev
    Next
    INDEX
    Explanations

    code or data snippets

    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
     dumpsters
    -0.26
     burge
    -0.24
    æĦ«
    -0.24
     Posté
    -0.24
    女æĢ§æľĭåıĭ
    -0.23
     disag
    -0.22
    umberland
    -0.21
     Whe
    -0.21
    ,},↵
    -0.20
    代è¨Ģ
    -0.19
    POSITIVE LOGITS
    å§ĭ建
    0.25
    âĦī
    0.25
     difficoltÃł
    0.24
    .nanoTime
    0.24
     licensors
    0.23
    LATED
    0.23
    æijĩäºĨ
    0.23
    /copyleft
    0.22
    rvine
    0.22
     withStyles
    0.21
    Activations Density 0.279%

    No Known Activations