© 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. 2010
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     fkk
    -0.50
     ×Ķ×ķ×ĵ
    -0.38
    å¿ŀ
    -0.37
     backpage
    -0.32
     pupper
    -0.32
     yarg
    -0.31
     beÄŁen
    -0.30
    æ·ı
    -0.30
     Atat
    -0.30
    ecycle
    -0.29
    POSITIVE LOGITS
    0.28
    s
    0.28
     s
    0.25
     in
    0.24
     to
    0.24
     M
    0.22
     .
    0.22
     same
    0.22
     of
    0.22
     on
    0.22
    Activations Density 1.045%

    No Known Activations