© 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. 129143
    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
     mess
    -0.32
    chner
    -0.30
    ickey
    -0.28
    anny
    -0.27
    stell
    -0.27
    stab
    -0.27
    agna
    -0.26
    ITHER
    -0.26
    åħ
    -0.26
     Robbins
    -0.25
    POSITIVE LOGITS
    çļĵ
    0.33
    -push
    0.26
     seal
    0.25
    -election
    0.24
    sealed
    0.24
    éļ¾éģĵ
    0.24
    lime
    0.23
    å¹´éĻIJ
    0.23
    ä¸Ģ个å°ıæŶ
    0.23
    个å¤ļå°ıæŶ
    0.23
    Activations Density 5.136%

    No Known Activations

    This feature has no known activations.