© 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. 1825
    Prev
    Next
    INDEX
    Explanations

    announcements and status

    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
    äºĭåĦ¿
    -0.23
    ization
    -0.23
    	StringBuffer
    -0.22
     .↵↵↵↵
    -0.21
    Wiki
    -0.20
    ï½Ľ
    -0.20
    çİ°å¦Ĥä»Ĭ
    -0.20
     beneficiation
    -0.20
    å¾ĢåIJİ
    -0.19
    åºĶæĢ¥ç®¡çIJĨ
    -0.19
    POSITIVE LOGITS
    iferay
    0.28
    iculty
    0.25
     ++)↵
    0.24
    braska
    0.23
    FormattedMessage
    0.23
    illisecond
    0.22
    ikhail
    0.22
    riday
    0.22
    phalt
    0.21
    ptune
    0.21
    Activations Density 0.738%

    No Known Activations