© 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. 4378
    Prev
    Next
    INDEX
    Explanations

    text 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
    çİ¢
    -0.24
    ä¿£
    -0.22
    çijĻ
    -0.21
    endencies
    -0.21
    .HandlerFunc
    -0.20
    ingleton
    -0.20
    å®ŀäºĭæ±Ĥ
    -0.19
    {{{
    -0.19
    )))));↵
    -0.19
     '%$
    -0.19
    POSITIVE LOGITS
    malink
    0.21
    ddie
    0.19
     patt
    0.19
    пи
    0.19
    ugeot
    0.19
    顺
    0.18
    Ļ¶
    0.18
    éĶĽ
    0.18
    [section
    0.18
    éłĨ
    0.18
    Activations Density 0.004%

    No Known Activations