© 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. 2061
    Prev
    Next
    INDEX
    Explanations

    code and structure

    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
    âĢ¦↵↵↵↵
    -0.31
    curacy
    -0.29
    -strokes
    -0.29
     tats
    -0.26
    âĨ©
    -0.25
     )))
    -0.24
     [âĢ¦]↵↵
    -0.24
     ×Ķ×ķ×ĵ
    -0.24
    :'',
    -0.24
     èĩªåĬ¨çĶŁæĪIJ
    -0.23
    POSITIVE LOGITS
    .↵
    0.52
    ,↵
    0.45
    ",↵
    0.42
    !↵
    0.40
     .↵
    0.39
    "↵
    0.38
    ãĢĤ↵
    0.38
    ".↵
    0.37
    ',↵
    0.37
     *,↵
    0.37
    Activations Density 0.619%

    No Known Activations