© 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. 4368
    Prev
    Next
    INDEX
    Explanations

    citations 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
     practition
    -0.33
    -Cs
    -0.30
    /Framework
    -0.25
    /Runtime
    -0.25
    ')==
    -0.25
    egis
    -0.25
    :maj
    -0.23
    {}{↵
    -0.23
    ulary
    -0.23
    ',...↵
    -0.23
    POSITIVE LOGITS
    ãĤĮãģ¾ãģĻ
    0.19
     onResponse
    0.18
     onFailure
    0.18
    cult
    0.18
    addAll
    0.18
    son
    0.17
     Conexion
    0.17
    åħ¬
    0.17
     liebe
    0.17
    alt
    0.17
    Activations Density 0.198%

    No Known Activations