© 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. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6463
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plode
    -0.27
    æģ¢å¤į
    -0.26
    ä»Ģä¹Īäºĭ
    -0.25
     restoration
    -0.25
     Richt
    -0.25
    çļĦä¸Ģç§į
    -0.25
    认åIJĮ
    -0.24
    å£ij
    -0.24
     explode
    -0.24
     rupt
    -0.24
    POSITIVE LOGITS
     Sidd
    0.29
    èį£å¹¸
    0.25
    并ä¸į代表
    0.25
    èĮŃ
    0.25
    nement
    0.24
     Sesso
    0.24
    =http
    0.24
    Website
    0.23
     JAXBElement
    0.23
    aster
    0.23
    Activations Density 0.098%

    No Known Activations

    This feature has no known activations.