© 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. 4093
    Prev
    Next
    INDEX
    Explanations

    practice

    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
    :params
    -0.25
    (QStringLiteral
    -0.21
     fitte
    -0.21
    çĹĬ
    -0.20
    åį§
    -0.20
     fkk
    -0.20
    (Gravity
    -0.20
    ucson
    -0.20
    }->
    -0.20
    imet
    -0.20
    POSITIVE LOGITS
     practice
    0.29
    practice
    0.28
     Practice
    0.28
    æī§ä¸ļ
    0.26
    Practice
    0.25
     Pract
    0.24
    å®ŀè·µ
    0.23
    åIJĮä»ģ
    0.23
     practicing
    0.23
    åŁ·
    0.23
    Activations Density 1.554%

    No Known Activations