© 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. 4134
    Prev
    Next
    INDEX
    Explanations

    middle or intermediate

    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
    æľĢåIJİ
    -0.25
    æľĢåIJİä¸Ģ
    -0.24
    æľĢå¾Į
    -0.23
    égor
    -0.22
    ç»Īæŀģ
    -0.22
     Final
    -0.22
    udiantes
    -0.21
    itus
    -0.21
     topping
    -0.20
    iane
    -0.20
    POSITIVE LOGITS
    ä¸ŃæľŁ
    0.44
     Intermediate
    0.42
    ä¸ŃéĹ´
    0.41
    Intermediate
    0.40
     intermediate
    0.40
     middle
    0.38
     second
    0.37
    second
    0.35
    第äºĮ个
    0.35
    ä¸Ń级
    0.34
    Activations Density 0.512%

    No Known Activations