© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4387
    Prev
    Next
    INDEX
    Explanations

    family relationships

    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
    Negative Logits
    对èĩªå·±çļĦ
    -0.25
    .InnerException
    -0.24
    нÑģкаÑı
    -0.21
    äºĨèĩªå·±çļĦ
    -0.21
    stituição
    -0.20
    综åIJĪæķ´æ²»
    -0.20
    对èĩªå·±
    -0.20
     سبØŃاÙĨÙĩ
    -0.20
     personally
    -0.20
    izabeth
    -0.19
    POSITIVE LOGITS
    abcdefghijklmnop
    0.23
    âĮĺ
    0.22
    æIJĢ
    0.21
    åĤ¬
    0.20
    :convert
    0.20
    é¼¾
    0.20
    íŀĺ
    0.20
    ãĤĴè¦ĭãģĽ
    0.20
    abcdefghijkl
    0.19
    ä¸įåIJĮæĦı
    0.19
    Activations Density 0.602%

    No Known Activations