© 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. 2513
    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
    '].'/
    -0.25
    /Area
    -0.23
    ();++
    -0.22
    æĵį
    -0.21
    åĬ¨çĶŁæĪIJ
    -0.20
    )")
    -0.20
    (Photo
    -0.20
    è¢
    -0.20
    дÑĢа
    -0.19
    .chomp
    -0.19
    POSITIVE LOGITS
     filmy
    0.23
     fierc
    0.21
    ourd
    0.20
     buflen
    0.20
    ĶåĽŀ
    0.19
    éducation
    0.19
    èĶ
    0.19
    vasion
    0.18
    ãģ£ãģ¦ãģĬãĤĬãģ¾ãģĻ
    0.18
     rematch
    0.18
    Activations Density 0.001%

    No Known Activations