© 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. 959
    Prev
    Next
    INDEX
    Explanations

    programming terms

    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
    isseur
    -0.25
     {?}
    -0.23
    -wow
    -0.22
     {?>↵
    -0.22
     ########.
    -0.22
    Hillary
    -0.22
     safezone
    -0.21
    fillType
    -0.21
     scn
    -0.21
    ANDOM
    -0.21
    POSITIVE LOGITS
     CircularProgress
    0.29
    é»ijæģ¶
    0.25
    /*↵
    0.24
     label
    0.24
    .FileReader
    0.23
    nodeName
    0.22
    è´¸æĺĵæĪĺ
    0.22
    LineStyle
    0.21
    vang
    0.21
     left
    0.21
    Activations Density 0.090%

    No Known Activations