© 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. 1511
    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
    æĭħè´Ł
    -0.20
     }),↵↵
    -0.20
    èģļ
    -0.19
    æĬĺ
    -0.19
    .loadData
    -0.18
    éĴIJ
    -0.18
    ughters
    -0.18
    nore
    -0.18
    º
    -0.17
     horm
    -0.17
    POSITIVE LOGITS
    >manual
    0.31
    togroup
    0.27
    erable
    0.24
     millenn
    0.23
    åĨħ马
    0.23
     ØŃÙĤÙĬÙĤÙĬ
    0.23
     èĩªåĬ¨çĶŁæĪIJ
    0.23
     safeg
    0.23
    (iOS
    0.22
    ->{_
    0.22
    Activations Density 0.001%

    No Known Activations