© 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. 820
    Prev
    Next
    INDEX
    Explanations

    usernames and numbers

    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
    gnore
    -0.23
    .AI
    -0.23
    أخÙĪ
    -0.22
    æĺŁå·´
    -0.22
    .yy
    -0.22
    åij£
    -0.21
    Ø£Ùģر
    -0.21
        	č↵
    -0.20
    egot
    -0.20
     Ø£ÙģرÙĬ
    -0.20
    POSITIVE LOGITS
    oriously
    0.25
    âĸİ
    0.25
     beÄŁen
    0.24
    æīĢæīĢ
    0.22
    娣
    0.22
    æĪij羣çļĦ
    0.22
     \''
    0.21
    ãĪ
    0.21
     bureaucr
    0.21
    å§Ķç»Ħç»ĩéĥ¨
    0.20
    Activations Density 2.010%

    No Known Activations