© 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. 19-TRANSCODER-HP
    7. 9664
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĤ¬æµ®
    -0.25
    ordes
    -0.25
    porto
    -0.24
    -how
    -0.24
    ĥģ
    -0.24
    ä»ĸæĺ¯
    -0.24
    reek
    -0.24
    uitar
    -0.23
    lius
    -0.23
    utherland
    -0.23
    POSITIVE LOGITS
     integral
    0.29
     Integral
    0.28
    anity
    0.26
    çݯçIJĥ
    0.26
     Structure
    0.25
     loop
    0.25
     cấp
    0.25
     auto
    0.24
     remotely
    0.24
     Loop
    0.24
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.