© 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. 142582
    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
    çĤ½
    -0.27
    ylv
    -0.25
    ighthouse
    -0.25
    osit
    -0.24
    Absent
    -0.24
    çĮ·
    -0.24
    ä¹ĭä¸Ģ
    -0.24
    orners
    -0.24
    onso
    -0.23
    Witness
    -0.23
    POSITIVE LOGITS
    è¹ij
    0.24
    eries
    0.24
     darkness
    0.24
    éªĹåıĸ
    0.24
     jeopardy
    0.23
    讲述äºĨ
    0.23
     tally
    0.22
    çī©ä»·
    0.22
     vocab
    0.22
    å½ĵä½ł
    0.22
    Activations Density 2.761%

    No Known Activations

    This feature has no known activations.