© 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. 1185
    Prev
    Next
    INDEX
    Explanations

    blog

    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
    /↵↵↵↵
    -0.28
    åĵĪåĵĪåĵĪåĵĪ
    -0.26
    æIJĽ
    -0.25
    ulton
    -0.25
    æľĭåıĭ们对
    -0.24
     helicopt
    -0.24
     snapchat
    -0.24
    ushman
    -0.22
    è°²
    -0.22
    'icon
    -0.22
    POSITIVE LOGITS
     blog
    0.40
    äºĨæĪijçļĦ
    0.34
     my
    0.33
    -blog
    0.33
    blog
    0.33
     Blog
    0.31
    Blog
    0.30
    æĺ¯æĪij
    0.29
    åĽłä¸ºæĪij
    0.28
    æĪijçļĦ
    0.28
    Activations Density 7.467%

    No Known Activations