© 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. 142579
    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
    quisite
    -0.25
    å·Ŀ
    -0.24
    fan
    -0.24
    ="<
    -0.24
     kø
    -0.24
    ainers
    -0.23
    ãģĭãĤĭ
    -0.23
    ä¸įåİ»
    -0.23
    quisites
    -0.23
     jan
    -0.23
    POSITIVE LOGITS
     Creed
    0.28
     ÑĤÑĢав
    0.24
    -REAL
    0.24
    æ¶Įåħ¥
    0.24
    åį°è±¡
    0.24
    è¿Ľåħ¥äºĨ
    0.24
    éªĪ
    0.23
    è¿Ļ两年
    0.23
    夹
    0.23
    REA
    0.23
    Activations Density 17.839%

    No Known Activations

    This feature has no known activations.