© 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. 3085
    Prev
    Next
    INDEX
    Explanations

    news and media

    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
    并ä¸İ
    -0.21
    åīįæīĢ
    -0.20
    IRE
    -0.20
    navbarSupportedContent
    -0.19
     Gon
    -0.19
     Fer
    -0.18
    ="'.
    -0.18
    ovenant
    -0.18
    .setItem
    -0.17
    ibus
    -0.17
    POSITIVE LOGITS
     bindActionCreators
    0.26
     TMPro
    0.23
     withRouter
    0.22
    steder
    0.22
    noinspection
    0.21
    duto
    0.21
     Widow
    0.21
    ä»ķ
    0.20
    iferay
    0.20
    igm
    0.19
    Activations Density 0.001%

    No Known Activations