© 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. 913
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åħļé£İ
    -0.24
    诸侯
    -0.21
    游æĪıè£ħå¤ĩ
    -0.21
    .DeserializeObject
    -0.19
    kiego
    -0.19
    æĵŀ
    -0.19
    italize
    -0.19
    ç£ĭ
    -0.18
    æijĩäºĨ
    -0.18
    /frontend
    -0.18
    POSITIVE LOGITS
     }):
    0.22
    ummings
    0.22
    CESS
    0.21
     backpage
    0.20
     airstrikes
    0.20
    ucson
    0.20
     ><?
    0.20
    µľ
    0.19
     Loren
    0.19
     PÃ¥
    0.18
    Activations Density 0.001%

    No Known Activations