© 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. 131161
    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
    iens
    -0.32
    代价
    -0.27
    heck
    -0.27
    anoi
    -0.26
    æºIJæºIJä¸įæĸŃ
    -0.25
    æĬ¥ç¤¾
    -0.25
    ivo
    -0.24
    xdb
    -0.24
    æĭĩ
    -0.24
    å¹³åĿĩæ¯ı
    -0.23
    POSITIVE LOGITS
    å¸Ī
    0.29
     distinction
    0.28
    nect
    0.26
    Stand
    0.25
    åĪĴ
    0.25
    æľºåĪ¶
    0.24
    èĢĮæĺ¯
    0.24
    indre
    0.23
    ä¸Ģå¾ĭ
    0.23
     lit
    0.23
    Activations Density 2.326%

    No Known Activations

    This feature has no known activations.