© 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. 1670
    Prev
    Next
    INDEX
    Explanations

    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
    ä¹ı
    -0.22
    .ecore
    -0.21
    åĵĤ
    -0.19
    /tinyos
    -0.19
    æĴ¤
    -0.19
    imagenes
    -0.19
    -Cs
    -0.18
    akest
    -0.18
    gages
    -0.18
    AST
    -0.17
    POSITIVE LOGITS
     ntohs
    0.24
    .FlatStyle
    0.24
     fireEvent
    0.23
    Äİ
    0.22
    é½
    0.21
    DMETHOD
    0.20
    -ignore
    0.20
    erase
    0.19
    ruc
    0.19
    $headers
    0.19
    Activations Density 0.001%

    No Known Activations