© 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. 755
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     ×Ķ×ķ×ĵ
    -0.23
    ï¹ı
    -0.23
    ,,,,,,,,
    -0.23
     AndAlso
    -0.21
    ograms
    -0.21
    ç¶ļãģįãĤĴèªŃãĤĢ
    -0.21
    osemite
    -0.20
     ();
    -0.20
    /generated
    -0.20
    >'+
    -0.20
    POSITIVE LOGITS
     çļĦ
    0.24
    .tagName
    0.23
    /');↵
    0.21
    -addons
    0.21
     homers
    0.21
    ámara
    0.20
        ↵    ↵    ↵    ↵
    0.20
    âĢ²
    0.20
    _codegen
    0.20
    adors
    0.20
    Activations Density 5.900%

    No Known Activations