© 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. 1496
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    izzas
    -0.22
    HomeAsUp
    -0.22
     ucwords
    -0.21
    .userInteractionEnabled
    -0.21
    -threat
    -0.21
    etu
    -0.20
    奥巴
    -0.20
    ViewById
    -0.20
    ByText
    -0.19
    åij£
    -0.19
    POSITIVE LOGITS
    iden
    0.20
    auga
    0.19
     HtmlWebpackPlugin
    0.19
    ä¼ijéĹ²
    0.18
    getList
    0.18
    	glEnable
    0.18
    ÙĪبا
    0.18
    ĴĮ
    0.18
    èĤ¥
    0.17
     functional
    0.17
    Activations Density 0.001%

    No Known Activations