© 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. 174
    Prev
    Next
    INDEX
    Explanations

    scientific technical terms

    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
    游æĪı代
    -0.27
    游æĪıæĬĢå·§
    -0.24
     Vulkan
    -0.23
    orners
    -0.22
    ysize
    -0.22
    aramel
    -0.21
    usercontent
    -0.21
    .SelectedIndexChanged
    -0.21
    -Compatible
    -0.21
    CADE
    -0.21
    POSITIVE LOGITS
     slik
    0.23
     porno
    0.22
     offsetX
    0.21
     UIAlert
    0.19
    emer
    0.19
     centerX
    0.19
    æģģ
    0.18
    èªĵ
    0.18
     minX
    0.18
    被æīĵ
    0.18
    Activations Density 0.012%

    No Known Activations