© 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. 142557
    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
    ÄĻż
    -0.27
    upon
    -0.26
    /videos
    -0.26
    é¡¿
    -0.24
    ARIANT
    -0.24
    ARRAY
    -0.24
    éģĩ
    -0.23
    é¹
    -0.23
    æŃ»
    -0.23
    ä¸Ģé¦ĸ
    -0.23
    POSITIVE LOGITS
     document
    0.33
    document
    0.28
     Orchard
    0.27
    ots
    0.26
    ocz
    0.26
    æ¯ĶåĪĨ
    0.24
    -document
    0.24
    å¼ıçļĦ
    0.24
    åħ¨åĽ½
    0.24
    -dominated
    0.24
    Activations Density 10.431%

    No Known Activations

    This feature has no known activations.