© 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. 2714
    Prev
    Next
    INDEX
    Explanations

    actions

    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
    æİ¥åĪ°
    -0.20
    )'),
    -0.19
    endet
    -0.19
    æ¦ľ
    -0.18
    .showMessage
    -0.18
    !!)↵
    -0.18
    éĹ´æİ¥
    -0.18
    æįĭ
    -0.18
     deter
    -0.18
    è¦ģåıĬæŶ
    -0.18
    POSITIVE LOGITS
    帮å¿Ļ
    0.32
    帮æĪij
    0.26
    帮ä»ĸ
    0.24
    /commons
    0.23
    Promise
    0.23
    нибÑĥдÑĮ
    0.22
    为æĪij们
    0.22
    crast
    0.21
     Promise
    0.21
    为åħ¶
    0.21
    Activations Density 0.351%

    No Known Activations