© 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. 108626
    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
     caval
    -0.28
    主æĦı
    -0.25
     dy
    -0.25
    æŁĦ
    -0.25
     Proud
    -0.25
     onNext
    -0.25
     roar
    -0.24
    ForResult
    -0.24
     voices
    -0.24
    æľĪæľ«
    -0.24
    POSITIVE LOGITS
    éĢĤåºĶ
    0.31
     adaptation
    0.31
    æ¸Ĭ
    0.29
     adapting
    0.29
     adapt
    0.29
     adap
    0.29
    ooth
    0.28
     adaptations
    0.28
    axis
    0.27
    плаÑĤ
    0.27
    Activations Density 25.608%

    No Known Activations

    This feature has no known activations.