© 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. 62573
    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
    æĸ¹åIJijçĽĺ
    -0.30
    å§ĭç»Īä¿ĿæĮģ
    -0.25
     infused
    -0.25
    åħ¶æ¬¡æĺ¯
    -0.25
    agon
    -0.24
    çŃ¾ç½²äºĨ
    -0.24
    licht
    -0.24
     hood
    -0.23
    çŁŃè§Ĩé¢ij
    -0.23
     King
    -0.23
    POSITIVE LOGITS
    ArrayOf
    0.32
    æĿ¥çļĦ
    0.30
     emulation
    0.27
    ymous
    0.26
    ahl
    0.26
    å¢ī
    0.25
    gene
    0.25
    portfolio
    0.25
    好å¤ļ
    0.25
    _]
    0.25
    Activations Density 4.133%

    No Known Activations

    This feature has no known activations.