© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129110
    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
    Negative Logits
    gon
    -0.31
    lio
    -0.28
     sorted
    -0.27
    fort
    -0.27
     protection
    -0.26
    å°¼
    -0.26
    tom
    -0.26
    汤
    -0.25
    çľĭ
    -0.25
    hek
    -0.25
    POSITIVE LOGITS
    emes
    0.30
    éĥ¨åĪĨåĨħ容
    0.26
    æĸ°ä¸ī
    0.26
    ä¸įåıĬ
    0.26
    æĹ¥åĩĮæĻ¨
    0.25
    union
    0.24
    å¤ļåľ°
    0.24
    æļĸæ°Ķ
    0.24
    èIJ½åı¶
    0.24
    æĹ©ä¸Ĭ
    0.24
    Activations Density 33.989%

    No Known Activations

    This feature has no known activations.