© 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. 9414
    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
    jam
    -0.29
    dw
    -0.27
    ew
    -0.27
    è¯ķ
    -0.27
    zer
    -0.26
    éĢĨè¡Į
    -0.25
    éĻ¨
    -0.25
    éļ¶å±ŀ
    -0.25
    éĤ¢
    -0.25
    Hu
    -0.25
    POSITIVE LOGITS
     marshal
    0.32
     모ìĬµ
    0.26
     Beng
    0.26
     Contest
    0.25
     portrayed
    0.24
    nings
    0.24
     portrayal
    0.24
     Ladies
    0.24
    baugh
    0.24
    spect
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.