© 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. 4236
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ·¸
    -0.21
    ',{↵
    -0.21
     UIStoryboard
    -0.19
    []=$
    -0.19
    ĵĺ
    -0.19
    对åħ¶çľŁå®ŀ
    -0.19
     pParent
    -0.19
    âĦī
    -0.18
    çĽ¹
    -0.18
    erÃł
    -0.18
    POSITIVE LOGITS
     according
    0.54
    ä»ĸ说
    0.50
    她说
    0.48
    according
    0.46
    æį®
    0.44
     says
    0.43
    ä»ĸ认为
    0.43
     According
    0.41
     said
    0.39
    æį®ä»ĭç»į
    0.38
    Activations Density 0.489%

    No Known Activations