© 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. 4191
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    atican
    -0.24
    ottenham
    -0.21
    ucson
    -0.21
     JADX
    -0.21
    urnished
    -0.21
    å¨ħ
    -0.21
    -NLS
    -0.20
    utow
    -0.20
    ]int
    -0.20
    ampionship
    -0.20
    POSITIVE LOGITS
    æĸ°æµªè´¢ç»ı
    0.21
    âĸ½
    0.21
    å®ŀäºĭ
    0.21
    åŃĹ第
    0.21
    .UserInfo
    0.21
     giochi
    0.20
     presentViewController
    0.19
    createQuery
    0.19
    ä¸Ģ件äºĭæĥħ
    0.19
    è¿Ļ个èģĮä¸ļ
    0.19
    Activations Density 0.032%

    No Known Activations