© 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. 3299
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    np_max-act-logits · gemini-2.5-flash-lite
    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
     UClass
    -0.23
    FlowLayout
    -0.21
    .scalablytyped
    -0.21
    %X
    -0.21
    agne
    -0.20
    gratis
    -0.20
    é«ĺæ½®
    -0.20
    lem
    -0.19
    .rmtree
    -0.19
    .EventHandler
    -0.19
    POSITIVE LOGITS
    aeda
    0.21
    ãģĬå¾Ĺ
    0.21
    -strokes
    0.20
    ä¸Ģèĩ´å¥½è¯Ħ
    0.20
     misd
    0.20
     springfox
    0.20
    ]={↵
    0.20
     onDataChange
    0.20
    âļĹ
    0.19
     Disposable
    0.19
    Activations Density 0.005%

    No Known Activations