© 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. 9643
    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
    aments
    -0.28
    çIJ¯
    -0.27
    angan
    -0.26
    tors
    -0.26
    iere
    -0.25
    ursors
    -0.25
    æĹ©æĻļ
    -0.25
    mbH
    -0.25
    _strerror
    -0.25
    ellers
    -0.25
    POSITIVE LOGITS
    ilio
    0.30
    ç²¾åįİ
    0.28
    èĥ¸
    0.28
    åĨįæĿ¥
    0.26
     rex
    0.25
    æĭīå¼Ģ
    0.25
    ulses
    0.25
     tÆ°Æ¡ng
    0.25
     Reich
    0.25
     parch
    0.25
    Activations Density 0.281%

    No Known Activations

    This feature has no known activations.