© 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. 129921
    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
     Levin
    -0.30
    '.$
    -0.28
    è¿Ŀç«ł
    -0.26
    ä¸ªé¡¹çĽ®
    -0.25
    isks
    -0.25
    ovel
    -0.25
    éªĽ
    -0.25
    ogui
    -0.24
    ieves
    -0.24
     unas
    -0.24
    POSITIVE LOGITS
    =res
    0.26
    å¢ŀæĶ¶
    0.25
     sou
    0.24
    upy
    0.24
    populate
    0.24
    IEW
    0.24
    arth
    0.24
    ä¹Łåıªèĥ½
    0.24
    æĭ¼
    0.24
    /kernel
    0.24
    Activations Density 2.732%

    No Known Activations

    This feature has no known activations.