© 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. 720
    Prev
    Next
    INDEX
    Explanations

    population residents

    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
    æ°ijä¼ģ
    -0.22
    åħļçļĦåįģ
    -0.22
    æĪķ
    -0.21
     dames
    -0.21
    aku
    -0.20
    çĸ¡
    -0.20
    chrift
    -0.20
    å½ĵåľº
    -0.20
    æīįæĺ¯çľŁæŃ£
    -0.20
     HeaderComponent
    -0.20
    POSITIVE LOGITS
    stituição
    0.28
    âĸ¿
    0.25
    人åı£
    0.25
     population
    0.24
    æ°ij主çĶŁæ´»
    0.24
    æľīæľŁå¾Ĵ
    0.24
    人åĿĩ
    0.24
     residents
    0.23
    åIJijå¤ĸ
    0.23
     hosting
    0.23
    Activations Density 3.609%

    No Known Activations