© 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. 993
    Prev
    Next
    INDEX
    Explanations

    how

    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
    -Compatible
    -0.26
     Erectile
    -0.23
    |=↵
    -0.23
    unitÃł
    -0.21
     ×Ķ×ķ×ĵ
    -0.21
    .ibatis
    -0.20
    naments
    -0.20
     clearColor
    -0.20
    .gstatic
    -0.20
    		↵		↵		↵
    -0.19
    POSITIVE LOGITS
    soever
    0.31
    /how
    0.28
    )throws
    0.25
    [section
    0.24
    Cómo
    0.23
     exactly
    0.22
    gtest
    0.22
    对å¾ħ
    0.21
     else
    0.21
    itably
    0.21
    Activations Density 1.186%

    No Known Activations