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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 787
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    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
    âĸ·
    -0.29
    -AA
    -0.28
    âŀ¤
    -0.26
     èĩªåĬ¨çĶŁæĪIJ
    -0.26
    âĿĸ
    -0.24
    ".↵↵↵↵
    -0.23
    [âĢ¦
    -0.23
    :\"
    -0.23
    ,eg
    -0.23
    æĹłè®ºæĺ¯åħ¶
    -0.23
    POSITIVE LOGITS
     scaleY
    0.20
     spokeswoman
    0.20
    constexpr
    0.20
    /*****************************************************************************↵
    0.19
    桧
    0.19
     lav
    0.19
     Apocalypse
    0.19
    dataGridView
    0.19
    ά
    0.18
    ivement
    0.18
    Activations Density 1.479%

    No Known Activations