© 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. 2085
    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
    grily
    -0.23
    UrlParser
    -0.23
    ubbo
    -0.22
    riger
    -0.22
    --;↵↵
    -0.22
    Ø£ÙģÙĥار
    -0.22
    blr
    -0.22
    &o
    -0.21
    edback
    -0.21
    prech
    -0.21
    POSITIVE LOGITS
     PÃ¥
    0.21
     Karachi
    0.18
    æĺ¯è¦ģ
    0.18
    еÑĢа
    0.18
    棨
    0.18
     supers
    0.18
    好äºĭ
    0.18
     strconv
    0.17
    itis
    0.17
    å±
    0.17
    Activations Density 0.000%

    No Known Activations