© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
    -REAL
    -0.24
     connaît
    -0.23
     GANG
    -0.23
     Barrier
    -0.22
     Lad
    -0.22
    Ó¨
    -0.22
     Newest
    -0.21
    饺
    -0.21
    /↵↵↵↵
    -0.21
     èĩªåĬ¨çĶŁæĪIJ
    -0.21
    POSITIVE LOGITS
     poster
    0.23
     ?>"/>↵
    0.21
     Yayın
    0.20
    ä¸Ģèĩ´å¥½è¯Ħ
    0.20
     SpaÃŁ
    0.19
    ä¸ĢçĤ¹ä¹Łä¸į
    0.19
     quad
    0.19
     rehabilit
    0.18
     confirmPassword
    0.18
    xlim
    0.18
    Activations Density 0.002%

    No Known Activations