© 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. 5019
    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
     barg
    -0.26
    äººæł¼
    -0.26
     vad
    -0.24
     TForm
    -0.24
     comed
    -0.24
    å¿ĥæĥħ
    -0.23
     nowhere
    -0.23
     character
    -0.23
    è¾Ļ
    -0.23
     hurry
    -0.23
    POSITIVE LOGITS
    åĸĦ
    0.28
     tiêu
    0.24
    elman
    0.23
     isi
    0.23
    段
    0.23
    ìķ½
    0.23
    èĥ¶åĽĬ
    0.23
    ommen
    0.23
    éĤ£æ®µ
    0.23
    å¼Ĥ常
    0.23
    Activations Density 0.050%

    No Known Activations

    This feature has no known activations.