© 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. 142302
    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
    rese
    -0.28
    ivor
    -0.26
    ician
    -0.26
    åīįçŀ»
    -0.26
    为ä¸ŃåĽ½
    -0.25
    .Fill
    -0.25
    æĻ®
    -0.25
    reen
    -0.25
    _pri
    -0.25
     chast
    -0.24
    POSITIVE LOGITS
     ul
    0.24
     Journey
    0.24
     Employment
    0.24
     hứng
    0.24
    欢è¿İ大家
    0.23
    æĿ¥çľĭçľĭåIJ§
    0.23
    åįıä¼ļä¼ļéķ¿
    0.23
     Gambling
    0.23
    Hierarchy
    0.23
    èİ·å¾ĹæĦŁ
    0.23
    Activations Density 0.162%

    No Known Activations

    This feature has no known activations.