© 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. 62681
    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
    å¹³çŃī
    -0.26
    å¥Ń
    -0.26
     Gór
    -0.26
    è¿ĩåī©
    -0.24
     Wald
    -0.24
    顶
    -0.24
    lässig
    -0.23
    .interpolate
    -0.23
    å±±èĦī
    -0.23
    å¤ļä½Ļ
    -0.23
    POSITIVE LOGITS
    ween
    0.26
     uncert
    0.25
    æ¼¾
    0.25
     Ain
    0.25
    ä¸ĵé¢ĺ
    0.25
    糯
    0.24
    å°±ä¸įèĥ½
    0.24
     AIM
    0.24
    æĿ¼
    0.24
     burge
    0.24
    Activations Density 13.794%

    No Known Activations

    This feature has no known activations.