© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1113
    Prev
    Next
    INDEX
    Explanations

    news details

    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
    владе
    -0.23
    patibility
    -0.22
    ÑģлÑĥÑĪа
    -0.21
    .tar
    -0.21
    <TextView
    -0.21
    okino
    -0.21
    RectTransform
    -0.21
    SFML
    -0.21
    rvine
    -0.20
    GNUC
    -0.20
    POSITIVE LOGITS
    (CG
    0.22
    edException
    0.21
     locus
    0.20
    urrenc
    0.19
    foon
    0.19
    éta
    0.19
    æīĵãģ¡
    0.19
    "go
    0.19
    اÙħعة
    0.19
     Borough
    0.18
    Activations Density 0.001%

    No Known Activations