© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    brand/media names

    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
    åĨħ马
    -0.21
     sw
    -0.20
    >(()
    -0.20
    ĪæĿĥ
    -0.19
    åİī
    -0.19
    foundland
    -0.18
     actionPerformed
    -0.18
     stake
    -0.18
    eventName
    -0.18
    ãģ¦ãģıãĤĭ
    -0.18
    POSITIVE LOGITS
    arpa
    0.21
    èĤ¯
    0.20
    charted
    0.19
    ensed
    0.19
    ä¿ĥ
    0.19
    :<?
    0.18
    ensible
    0.18
     yans
    0.18
    ологиÑı
    0.18
    	mysqli
    0.17
    Activations Density 0.001%

    No Known Activations