© 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. 64732
    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
    emark
    -0.30
    对èĩªå·±çļĦ
    -0.26
    offline
    -0.25
    对å¾ħ
    -0.25
    TextInput
    -0.25
    åıĹæįŁ
    -0.25
    éĶĻäºĨ
    -0.25
     Wrong
    -0.25
     wrong
    -0.24
    {%
    -0.24
    POSITIVE LOGITS
    ç±³
    0.28
     ç±
    0.28
    MV
    0.26
    忽çķ¥
    0.26
    åĿĩæľī
    0.25
    canonical
    0.25
    综åIJĪ
    0.25
     MV
    0.25
     Tib
    0.25
    æĻ¾
    0.25
    Activations Density 51.482%

    No Known Activations

    This feature has no known activations.