© 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. 1840
    Prev
    Next
    INDEX
    Explanations

    change or modify

    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
    elaide
    -0.28
    ancybox
    -0.24
    ",-
    -0.23
    ðŁĺĢ
    -0.23
    /↵↵↵↵
    -0.23
    nych
    -0.23
    izzie
    -0.22
    ",{
    -0.22
    acades
    -0.21
    udget
    -0.21
    POSITIVE LOGITS
    /change
    0.35
    (change
    0.33
    æĶ¹åıĺäºĨ
    0.28
    /add
    0.28
    -change
    0.27
    å¹ħ度
    0.27
    .Change
    0.27
     change
    0.27
    æĶ¹åıĺ
    0.27
    à¹ģà¸Ľà¸¥
    0.27
    Activations Density 3.301%

    No Known Activations