© 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. 639
    Prev
    Next
    INDEX
    Explanations

    word parts

    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
    快讯
    -0.22
    "errors
    -0.22
    èĪĽ
    -0.21
    VertexArray
    -0.20
    isted
    -0.20
    .MouseAdapter
    -0.20
    æľªæĪIJ
    -0.20
    yms
    -0.20
     showAlert
    -0.19
    IÃĬ
    -0.19
    POSITIVE LOGITS
    prene
    0.24
     burge
    0.23
    roupon
    0.21
     pestic
    0.21
     desar
    0.21
    odore
    0.20
    LOBAL
    0.20
    oriously
    0.20
    _DBG
    0.19
     beneficiation
    0.19
    Activations Density 1.249%

    No Known Activations