© 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. 4138
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    indered
    -0.23
    鸢
    -0.23
     useHistory
    -0.20
    NumberOf
    -0.20
    omm
    -0.20
     didFinish
    -0.19
    aben
    -0.19
    bursement
    -0.19
    ãģĵãģ¨ãĤĤãģĤãĤĬãģ¾ãģĻ
    -0.19
    :both
    -0.19
    POSITIVE LOGITS
    æīĢæīĢ
    0.21
    :UIAlert
    0.21
     ==(
    0.20
     camb
    0.20
    ãĢĤwww
    0.20
    ä»İ严治
    0.20
     nues
    0.20
    以人为
    0.20
    é¦Ĵ
    0.19
    æĸ°åĬł
    0.19
    Activations Density 0.001%

    No Known Activations