© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2799
    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
    cratch
    -0.28
    eam
    -0.23
    odesk
    -0.23
    ynos
    -0.23
    ;};↵
    -0.22
    ANDOM
    -0.21
    tring
    -0.21
    -LAST
    -0.20
    VICE
    -0.20
    intendo
    -0.20
    POSITIVE LOGITS
    çĭ¼
    0.22
    xmlns
    0.20
     ern
    0.19
     burg
    0.18
    ol
    0.18
    GroupBox
    0.17
     Goth
    0.17
    um
    0.17
     flattering
    0.17
     helf
    0.17
    Activations Density 0.001%

    No Known Activations