© 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. 4778
    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
    è¿Ļ两ç§į
    -0.26
    igated
    -0.25
    /native
    -0.25
    ELY
    -0.24
    cence
    -0.24
     handled
    -0.23
    nestjs
    -0.23
    ful
    -0.23
    说è¿ĩ
    -0.23
     capture
    -0.23
    POSITIVE LOGITS
    æĺ¥æĻļ
    0.25
    ERT
    0.25
    è£ģ
    0.24
    çĪIJ
    0.24
    =<?=
    0.24
     shakes
    0.24
    æıī
    0.24
    صÙĦا
    0.24
    rou
    0.24
    aidu
    0.24
    Activations Density 0.193%

    No Known Activations

    This feature has no known activations.