© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3460
    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
    Türkiye
    -0.21
    飧
    -0.21
     mooie
    -0.20
    paper
    -0.19
    venture
    -0.19
    	Created
    -0.19
    age
    -0.19
     "#"
    -0.18
    comic
    -0.18
    é£Łãģ¹ãģ¦
    -0.18
    POSITIVE LOGITS
    esub
    0.25
    emean
    0.25
    abox
    0.24
    ipop
    0.22
    obierno
    0.22
    ptune
    0.22
    ervas
    0.22
    icions
    0.22
    ynet
    0.21
    cers
    0.21
    Activations Density 0.000%

    No Known Activations