© 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. 1961
    Prev
    Next
    INDEX
    Explanations

    during time

    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
    íĶĦë¡ľê·¸
    -0.25
    aeda
    -0.21
     prompt
    -0.21
    صط
    -0.20
     sigu
    -0.19
    .prompt
    -0.19
    âĦī
    -0.18
     avere
    -0.18
    /Typography
    -0.18
    åļĨ
    -0.18
    POSITIVE LOGITS
    æľŁéĹ´
    0.35
    æĹ¶æľŁ
    0.32
     periods
    0.32
     period
    0.31
     during
    0.29
     times
    0.26
    BOVE
    0.25
    etimes
    0.24
    æĹ¶æľŁçļĦ
    0.24
     During
    0.23
    Activations Density 1.115%

    No Known Activations