© 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. 4877
    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
    åĽłä¸ºä»ĸ们
    -0.34
     ApiController
    -0.28
    olib
    -0.25
    itives
    -0.25
    èįī
    -0.25
    åıĮåıĮ
    -0.24
    %</
    -0.24
    /[
    -0.24
    Prem
    -0.24
    è®´
    -0.24
    POSITIVE LOGITS
    第ä¸ĢæĿ¡
    0.29
    course
    0.25
    иÑĩ
    0.24
    è·¯ä¸Ĭ
    0.24
    appoint
    0.24
    ä¹°çļĦ
    0.23
    èµĦæĸĻ
    0.23
    ãĥ¼ãĤ¿ãĥ¼
    0.23
    JT
    0.23
     displ
    0.23
    Activations Density 0.057%

    No Known Activations

    This feature has no known activations.