© 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. 1931
    Prev
    Next
    INDEX
    Explanations

    say "wh" words

    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
    º«
    -0.23
    anuts
    -0.23
    ä¼ĹæīĢåij¨
    -0.21
    giene
    -0.21
    ä½łä¹Ł
    -0.21
    ?=
    -0.20
    -0.20
    ë¶
    -0.20
    för
    -0.20
    è®
    -0.19
    POSITIVE LOGITS
     whether
    0.73
     how
    0.72
    æĺ¯åIJ¦
    0.59
    whether
    0.58
    how
    0.57
     Whether
    0.57
    å¦Ĥä½ķ
    0.56
    èĥ½åIJ¦
    0.53
     æĺ¯åIJ¦
    0.51
     why
    0.50
    Activations Density 2.860%

    No Known Activations