© 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. 1860
    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
    rente
    -0.21
    nels
    -0.20
    å±ģèĤ¡
    -0.19
     TMPro
    -0.19
     Rif
    -0.18
     Interracial
    -0.18
     Fonts
    -0.18
     ámb
    -0.18
    issing
    -0.18
     })();↵
    -0.17
    POSITIVE LOGITS
    ä¸ĭéĿ¢æĺ¯å°ı
    0.27
     EntityState
    0.22
     moc
    0.21
    :convert
    0.21
    踽
    0.20
    awei
    0.20
    æŁģ
    0.20
    .assertNull
    0.20
     ila
    0.20
    utta
    0.19
    Activations Density 0.001%

    No Known Activations