© 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. 4197
    Prev
    Next
    INDEX
    Explanations

    file paths and licenses

    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
    è°¢éĤĢ
    -0.30
    /slider
    -0.28
    /Runtime
    -0.25
    ++){↵↵
    -0.25
    /modal
    -0.24
    /slick
    -0.24
    ;"><?
    -0.23
     ++)↵
    -0.23
    åıĪ好åıĪå¿«
    -0.23
    /tos
    -0.23
    POSITIVE LOGITS
    /
    0.27
     burge
    0.23
    éħŀ
    0.19
    代
    0.19
     Folder
    0.19
    unas
    0.19
    nego
    0.18
    IRTUAL
    0.18
    ixo
    0.18
     letterSpacing
    0.18
    Activations Density 0.277%

    No Known Activations