© 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. 1414
    Prev
    Next
    INDEX
    Explanations

    speaker attribution

    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
    HttpException
    -0.22
    stdarg
    -0.22
    -0.21
    ssel
    -0.20
    	finally
    -0.20
     screenSize
    -0.19
     PackageManager
    -0.19
     `}↵
    -0.19
    robots
    -0.19
     qreal
    -0.19
    POSITIVE LOGITS
    è¿Ļä½į
    0.36
    è¿ĻåIJį
    0.28
     him
    0.28
    ä»ĸ对
    0.27
     appré
    0.26
    ä»ĸåľ¨
    0.26
    ä»ĸ
    0.26
     Según
    0.25
    ;!
    0.25
    ä»ĸèĩªå·±
    0.24
    Activations Density 2.464%

    No Known Activations