© 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. 682
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    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
     typealias
    -0.22
    åĭł
    -0.21
    æ³ķ人
    -0.21
    eder
    -0.20
    åĹIJ
    -0.20
    TRS
    -0.20
     addslashes
    -0.20
    .BLL
    -0.19
    hapus
    -0.19
    :bg
    -0.19
    POSITIVE LOGITS
    incinn
    0.21
    togroup
    0.21
    æŦ
    0.20
    )((((
    0.20
    åħ¶ä»ĸ
    0.20
    Utc
    0.20
    TestFixture
    0.19
    SystemService
    0.19
    -redux
    0.19
    datable
    0.19
    Activations Density 0.001%

    No Known Activations