© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    question ans

    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
    Nama
    -0.23
     licensors
    -0.23
    .scalablytyped
    -0.21
    :numel
    -0.21
     кÑĥд
    -0.21
    ï¼ģ');↵
    -0.21
    对çħ§æ£ĢæŁ¥
    -0.21
    .nama
    -0.20
    ilmiÅŁ
    -0.20
    .ToDouble
    -0.20
    POSITIVE LOGITS
    assertFalse
    0.19
    ä¸ĬãģĮãĤĬ
    0.19
    åģľçīĮ
    0.18
    æĸ¹åľĨ
    0.18
    åĪĨç±»
    0.18
    æĸ¹æ¡Ī
    0.18
     groupBox
    0.18
     Schl
    0.17
    ãĤµãĤ¤
    0.17
     Mah
    0.17
    Activations Density 0.001%

    No Known Activations