© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1364
    Prev
    Next
    INDEX
    Explanations

    high-level positions

    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
     imageSize
    -0.29
     Erectile
    -0.27
    åıijå±ķ模å¼ı
    -0.25
     imageURL
    -0.23
     Premiership
    -0.23
     seedu
    -0.23
     imageName
    -0.23
    æĿ¨æ¬¢
    -0.23
     imgUrl
    -0.23
     fucks
    -0.23
    POSITIVE LOGITS
    æĸ°æµªè´¢ç»ı
    0.28
    毫æĹłçĸij
    0.28
    .centerX
    0.27
     çĶŁåij½åij¨æľŁ
    0.26
    -fw
    0.26
    è¦ģéĹ»
    0.26
     office
    0.25
     Office
    0.25
    ulumi
    0.25
    благо
    0.24
    Activations Density 4.292%

    No Known Activations