© 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. 140704
    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
    ographically
    -0.28
    angled
    -0.27
     dokÅĤadnie
    -0.26
    åĦ¿
    -0.26
    rzÄĻ
    -0.26
    erry
    -0.25
    ropa
    -0.25
     bö
    -0.24
    ç¡®
    -0.24
    ervice
    -0.24
    POSITIVE LOGITS
    对ä¼ģä¸ļ
    0.28
    caption
    0.26
    宣
    0.25
    为ä¼ģä¸ļ
    0.25
     UNS
    0.24
    aque
    0.24
    airy
    0.24
    _multiplier
    0.23
    对åħ¬åı¸
    0.23
    obo
    0.23
    Activations Density 3.371%

    No Known Activations

    This feature has no known activations.