© 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. 1701
    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
    ä¼Ĭæĭī
    -0.21
    ment
    -0.21
     elÅij
    -0.20
    éĩįè¦ģ举æݪ
    -0.20
     setFrame
    -0.20
    禤
    -0.19
    举æĸ¹è´¢å¯Į
    -0.19
     "/");↵
    -0.19
     culo
    -0.19
    asInstanceOf
    -0.18
    POSITIVE LOGITS
    ;break
    0.31
    .');
    0.30
    >'.↵
    0.30
    printStats
    0.27
    .cloudflare
    0.26
    ksam
    0.24
    |int
    0.24
    /lg
    0.24
     createState
    0.24
    -yyyy
    0.24
    Activations Density 0.260%

    No Known Activations