© 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. 591
    Prev
    Next
    INDEX
    Explanations

    growth and change

    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
    é«ĺåĩº
    -0.22
     McCart
    -0.21
    çĺ°
    -0.21
    AGAIN
    -0.20
    requencies
    -0.19
     "{\"
    -0.19
     frequent
    -0.19
    åģıä½İ
    -0.19
     removeFromSuperview
    -0.18
    åĨį次
    -0.18
    POSITIVE LOGITS
    éĢIJæ¸IJ
    0.40
     progress
    0.38
    ç¼ĵæħ¢
    0.38
    éĢIJæŃ¥
    0.38
     gradually
    0.36
     slowly
    0.36
    æ¸IJ
    0.36
     Progress
    0.35
    progress
    0.34
    è¿Ľç¨ĭä¸Ń
    0.34
    Activations Density 3.781%

    No Known Activations