© 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. 4303
    Prev
    Next
    INDEX
    Explanations

    food and dishes

    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
    grily
    -0.25
    frey
    -0.22
    é£Łåĵģ
    -0.22
     food
    -0.21
    çħ®
    -0.20
     foods
    -0.20
     UnityEditor
    -0.20
     useStyles
    -0.20
    upert
    -0.20
     Fayette
    -0.20
    POSITIVE LOGITS
    libft
    0.20
     sliders
    0.20
     servi
    0.20
    здание
    0.20
    iterals
    0.20
    twor
    0.20
    éĢłä»·
    0.20
     köz
    0.19
    游æĪıè£ħå¤ĩ
    0.19
     áll
    0.19
    Activations Density 0.283%

    No Known Activations