© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2966
    Prev
    Next
    INDEX
    Explanations

    adjective suffixes

    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
    >({
    -0.24
    ðŁĵIJ
    -0.23
    ized
    -0.23
    åĮĸçļĦ
    -0.22
    izado
    -0.22
    LLU
    -0.22
    UTH
    -0.21
    xeb
    -0.20
    StackNavigator
    -0.20
    ised
    -0.20
    POSITIVE LOGITS
    ä½ľçĶ¨
    0.27
    iếu
    0.23
    ive
    0.22
    itive
    0.22
    ative
    0.21
     role
    0.21
    partment
    0.21
     zeal
    0.21
    ¢åįķ
    0.20
    anean
    0.20
    Activations Density 0.755%

    No Known Activations