© 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. 4096
    Prev
    Next
    INDEX
    Explanations

    tables and lists

    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
    ookies
    -0.20
    focused
    -0.20
    aida
    -0.19
    楼çĽĺ
    -0.19
    èļģ
    -0.19
     Garrett
    -0.19
    iggins
    -0.19
    ä¾µçĬ¯
    -0.18
    aeda
    -0.18
    æĬµ
    -0.18
    POSITIVE LOGITS
     TMPro
    0.24
    >(*
    0.24
    specialchars
    0.21
    rients
    0.21
    :;"
    0.21
    *sp
    0.20
    :white
    0.20
    ertia
    0.20
    rous
    0.20
    -mf
    0.19
    Activations Density 0.002%

    No Known Activations