© 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. 3329
    Prev
    Next
    INDEX
    Explanations

    libraries

    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
    åĵ¨
    -0.25
     createStackNavigator
    -0.21
    æĪĹ
    -0.21
    BASEPATH
    -0.21
    åİĨåı²æĸ°
    -0.20
    sitemap
    -0.20
    netinet
    -0.20
    .mybatisplus
    -0.19
    WebpackPlugin
    -0.19
     çĶŁåij½åij¨æľŁ
    -0.19
    POSITIVE LOGITS
    .dll
    0.24
     library
    0.23
    ámara
    0.22
    (library
    0.20
     needed
    0.20
    åĮħ
    0.20
    odule
    0.20
    -library
    0.20
    ä¾ĺ
    0.20
     CDN
    0.19
    Activations Density 0.788%

    No Known Activations