© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63091
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uzu
    -0.34
    (Optional
    -0.32
    uess
    -0.29
    ueue
    -0.28
     unborn
    -0.28
    ansa
    -0.26
    æĹłç¼Ŀ
    -0.26
    ura
    -0.26
    é«ĺçŃī
    -0.25
    ubi
    -0.25
    POSITIVE LOGITS
     Garrison
    0.26
    读åIJİ
    0.26
    ä¾Ŀ
    0.25
    éĻįæ°´
    0.25
    store
    0.25
     standard
    0.24
    -funded
    0.24
     Keywords
    0.24
    éķĤ
    0.23
     rais
    0.23
    Activations Density 1.674%

    No Known Activations

    This feature has no known activations.