© 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. 4049
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     elÅij
    -0.23
     minden
    -0.22
     Decorating
    -0.20
     tatto
    -0.20
     Ä°l
    -0.19
     predecess
    -0.19
    çĿ¹
    -0.19
    اسÙĬ
    -0.19
     somew
    -0.19
     unfavor
    -0.19
    POSITIVE LOGITS
    strncmp
    0.23
    .DataBindings
    0.20
     strncmp
    0.20
    çī¢è®°ä½¿åij½
    0.20
    memcmp
    0.20
    .SelectedItem
    0.20
    :<?
    0.19
    :Event
    0.19
    )NULL
    0.19
    иÑĩеÑģ
    0.19
    Activations Density 0.000%

    No Known Activations