© 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. 3839
    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
    [--
    -0.23
     setPassword
    -0.23
    },{↵
    -0.21
    ewith
    -0.20
    èĮ¼
    -0.20
    akeup
    -0.20
     )->
    -0.20
    pmat
    -0.20
    :return
    -0.19
    .ErrorCode
    -0.19
    POSITIVE LOGITS
    ãİľ
    0.22
    FLT
    0.20
    ureen
    0.20
    ä»Ļ
    0.19
     xhttp
    0.19
    brtc
    0.19
    èĨ³
    0.19
    erus
    0.19
     Premiership
    0.19
    åģĥ
    0.19
    Activations Density 0.000%

    No Known Activations