© 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. 64613
    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
    ä¹ı
    -0.27
    壮
    -0.25
    rawing
    -0.25
    αι
    -0.25
    ometrics
    -0.24
    orf
    -0.24
    潮湿
    -0.24
    uts
    -0.24
    湿
    -0.24
    ItemSelected
    -0.24
    POSITIVE LOGITS
    çļĦåij³éģĵ
    0.28
    andler
    0.26
    getDescription
    0.25
    çĻ¯
    0.25
    ilder
    0.25
    åĵĨ
    0.25
    apon
    0.24
    å¿Ĩ
    0.24
    å¿¿
    0.24
     buck
    0.24
    Activations Density 1.524%

    No Known Activations

    This feature has no known activations.