© 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. 2383
    Prev
    Next
    INDEX
    Explanations

    event times and places

    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
     Annual
    -0.21
    .setVertical
    -0.21
    imizer
    -0.20
    åĩºå¸Ń
    -0.19
     annual
    -0.19
     Aren
    -0.19
    ÑĤелÑĮного
    -0.19
    ç¾ŀ
    -0.19
     appré
    -0.18
    æ¯ıå¹´
    -0.18
    POSITIVE LOGITS
    âı°
    0.23
    RowAt
    0.22
    OfMonth
    0.22
     kup
    0.21
    é¦Ĭ
    0.21
    å±ĬæŶ
    0.21
    will
    0.21
     ëĪĦ구
    0.20
    acements
    0.20
    家åĸ»
    0.20
    Activations Density 0.813%

    No Known Activations