© 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. 142763
    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
    udu
    -0.28
    åľ¨ä¸ŃåĽ½
    -0.28
    elor
    -0.26
    å±ħ室
    -0.25
    ivated
    -0.25
    zyst
    -0.25
    DataTask
    -0.24
    çĨŁ
    -0.24
    çĥ¬
    -0.24
     medi
    -0.24
    POSITIVE LOGITS
    riad
    0.28
     Tribune
    0.27
    rollable
    0.26
    Inspectable
    0.25
    ä¸Ĭæµ·è¯ģåĪ¸
    0.25
    rem
    0.24
    |unique
    0.24
    大æī¹
    0.24
    ermal
    0.23
     Excell
    0.23
    Activations Density 40.061%

    No Known Activations

    This feature has no known activations.