© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1014
    Prev
    Next
    INDEX
    Explanations

    left and right

    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
    urnished
    -0.34
    errated
    -0.29
    ngth
    -0.28
    ohana
    -0.28
    odesk
    -0.27
    iect
    -0.27
    acades
    -0.27
    oggler
    -0.27
    serter
    -0.27
    intégr
    -0.26
    POSITIVE LOGITS
    /right
    0.31
    íĶĦë¡ľê·¸
    0.29
    arrow
    0.25
    Ymd
    0.24
     çĶŁåij½åij¨æľŁ
    0.23
    -hand
    0.23
    줬
    0.23
    TÃľ
    0.21
    æĸ°å¾ģç¨ĭ
    0.21
    èIJ¥åķĨ
    0.21
    Activations Density 0.283%

    No Known Activations