© 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. 142553
    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
     Odyssey
    -0.27
    imetype
    -0.27
    確å®ļ
    -0.26
     selves
    -0.25
    çļĦ妻åŃIJ
    -0.24
     Minute
    -0.24
     OR
    -0.24
     AIDS
    -0.24
    çŃĶåį·
    -0.23
    åijĬè¯ī大家
    -0.23
    POSITIVE LOGITS
     dra
    0.27
    ilities
    0.27
    amide
    0.27
    æĬ¬
    0.26
    æ¯ķ
    0.25
    ר×Ļ×Ŀ
    0.25
     Adresse
    0.24
    绩
    0.24
    cie
    0.24
     eyebrow
    0.24
    Activations Density 17.118%

    No Known Activations

    This feature has no known activations.