© 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. 481
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    èIJ¥ä¸ļæī§
    -0.28
    eldom
    -0.26
    主èIJ¥ä¸ļ
    -0.25
    åħ¨èµĦåŃIJ
    -0.25
    éĩįè¦ģ举æݪ
    -0.24
    çŀł
    -0.24
    æijĩäºĨ
    -0.23
     LIABLE
    -0.23
    ="{!!
    -0.22
    uxtap
    -0.22
    POSITIVE LOGITS
    FormattedMessage
    0.27
    !=(
    0.23
    Ùİا
    0.23
    .toCharArray
    0.23
    <=$
    0.23
     IsNot
    0.22
     että
    0.22
    bestos
    0.22
    meldung
    0.22
    ÂŃing
    0.21
    Activations Density 0.894%

    No Known Activations