© 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. 2618
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    "crypto
    -0.30
    "errors
    -0.22
     NavLink
    -0.22
    oxic
    -0.21
    æĮĪ
    -0.20
    "sync
    -0.20
    .SelectedItem
    -0.19
    AMI
    -0.19
    )throws
    -0.19
    æĢı
    -0.19
    POSITIVE LOGITS
    ðŁĮ°
    0.22
    ItemClick
    0.21
    å©´
    0.19
    æĵ¤
    0.19
     khá»ıi
    0.19
    åĽĽå¤Ħ
    0.19
    ynos
    0.19
     AuÃŁen
    0.19
    pson
    0.19
    Occurs
    0.18
    Activations Density 0.001%

    No Known Activations