© 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. 9466
    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
    æ³ķè§Ħ
    -0.27
    .pivot
    -0.26
     Share
    -0.25
    stim
    -0.25
    æ°´æºIJ
    -0.24
     inev
    -0.24
    asje
    -0.24
    _VIS
    -0.23
    tower
    -0.23
    è°§
    -0.23
    POSITIVE LOGITS
     trá»ĭ
    0.30
     locally
    0.27
     scar
    0.27
    _href
    0.27
    å·®å¼ĤåĮĸ
    0.26
     search
    0.25
     IActionResult
    0.24
    çį¨
    0.24
    åįķçĭ¬
    0.24
    arn
    0.23
    Activations Density 1.458%

    No Known Activations

    This feature has no known activations.