© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1984
    Prev
    Next
    INDEX
    Explanations

    document structure

    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
    Not in Any Lists

    No Comments

    Negative Logits
     strugg
    -0.24
    游æĪıæĵįä½ľ
    -0.21
     ofApp
    -0.21
    nyder
    -0.21
     ADVISED
    -0.21
    åĹ«
    -0.21
    rvine
    -0.21
    incinn
    -0.21
    çļĦæ°Ķæģ¯
    -0.21
     سبØŃاÙĨÙĩ
    -0.20
    POSITIVE LOGITS
    .Does
    0.23
     ÑĥвелиÑĩи
    0.22
     doi
    0.20
    å·¦
    0.20
    .Today
    0.20
     Bold
    0.19
    :left
    0.19
     legend
    0.19
    éķIJ
    0.19
    .StatusOK
    0.19
    Activations Density 0.089%

    No Known Activations