© 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. 9415
    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
    aeda
    -0.33
    梢
    -0.26
     king
    -0.25
    çłº
    -0.25
    bdb
    -0.25
    åªĴ
    -0.24
    ptive
    -0.24
    ldb
    -0.24
    uku
    -0.24
    semb
    -0.24
    POSITIVE LOGITS
    æīĢæīĢ
    0.25
     drops
    0.25
    STACK
    0.25
     vÃŃ
    0.25
    ä¸įçĦ¶
    0.24
     displays
    0.24
    -TV
    0.24
     szczegóÅĤowo
    0.24
     prop
    0.24
    .true
    0.24
    Activations Density 0.044%

    No Known Activations

    This feature has no known activations.