© 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. 2374
    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
    <decltype
    -0.24
    .Sup
    -0.22
    æĴµ
    -0.21
    é¾ĥ
    -0.21
    âļĹ
    -0.21
    .Spring
    -0.20
    趿
    -0.20
    pv
    -0.20
    âĦħ
    -0.19
    .scalajs
    -0.19
    POSITIVE LOGITS
     oma
    0.21
    аблиÑĨ
    0.21
    å®ļäºĨ
    0.21
    ÑĤвеÑĢ
    0.20
    éªĺ
    0.19
    quin
    0.19
     élevé
    0.18
    encodeURIComponent
    0.18
    ewe
    0.18
    orna
    0.18
    Activations Density 0.002%

    No Known Activations