© 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. 142646
    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
    agos
    -0.28
    uds
    -0.27
    mps
    -0.26
    æĺ¯æ²¡æľī
    -0.26
    andom
    -0.25
    поÑĢ
    -0.25
    irie
    -0.25
     ÑħаÑĢакÑĤеÑĢиÑģÑĤ
    -0.24
    .port
    -0.24
     dun
    -0.24
    POSITIVE LOGITS
     Yaz
    0.27
    æ£
    0.26
    oris
    0.26
    æ©ĺ
    0.24
    缴è¨Ģ
    0.24
    å¿Ļç¢Į
    0.24
    令人
    0.24
    ä¸ĢæĶ¯
    0.23
    棱
    0.23
    çĤİçĥŃ
    0.23
    Activations Density 1.882%

    No Known Activations

    This feature has no known activations.