© 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. 1916
    Prev
    Next
    INDEX
    Explanations

    privacy and cookies

    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
    .apiUrl
    -0.25
     FontWeight
    -0.22
     nye
    -0.21
    æĴĤ
    -0.21
     apiUrl
    -0.21
    åĩĩ
    -0.20
     nouve
    -0.20
    hores
    -0.20
    retweeted
    -0.20
    	snprintf
    -0.19
    POSITIVE LOGITS
     Privacy
    0.32
     privacy
    0.29
     cookies
    0.28
    éļIJç§ģ
    0.28
     Cookies
    0.28
    Privacy
    0.27
     Datensch
    0.26
     consent
    0.25
    个人信æģ¯
    0.25
    cookies
    0.25
    Activations Density 0.953%

    No Known Activations