© 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. 4115
    Prev
    Next
    INDEX
    Explanations

    historical rulers

    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
    repid
    -0.26
    nze
    -0.24
    /DD
    -0.23
    -Trump
    -0.22
    epy
    -0.22
    èµī
    -0.20
    ElementsBy
    -0.20
    .jsoup
    -0.20
    æ±Ĩ
    -0.20
     europé
    -0.19
    POSITIVE LOGITS
    '])){
    0.25
    溦
    0.22
    éģ¥æݧ
    0.22
     puppet
    0.21
     $("<
    0.21
    åĨ°æ·ĩ
    0.21
    æݧåĪ¶
    0.21
     FindObjectOfType
    0.20
    äºĨ好åĩł
    0.20
    incinn
    0.20
    Activations Density 0.325%

    No Known Activations