© 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. 1590
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     for
    -0.26
    ãģįãģ¡ãĤĵ
    -0.25
    å¸ħåĵ¥
    -0.24
    为广大
    -0.24
    ãģįãģ¡ãĤĵãģ¨
    -0.23
     "%"
    -0.23
    ãģĬäºĴãģĦ
    -0.22
    ãģĤãĤĭç¨ĭ度
    -0.22
    	for
    -0.21
     sovere
    -0.21
    POSITIVE LOGITS
     purposes
    0.55
     sake
    0.52
    bidden
    0.47
     reasons
    0.41
    geries
    0.37
    byss
    0.34
     (;;)
    0.33
    ergus
    0.32
    OCUS
    0.32
    /↵↵↵↵
    0.32
    Activations Density 1.612%

    No Known Activations