© 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. 32-TRANSCODER-HP
    7. 44125
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æł¹åŁº
    -0.30
    fl
    -0.28
    寸
    -0.28
    åĪĢ
    -0.27
    å¼
    -0.26
    lege
    -0.25
     Anch
    -0.25
    骨干
    -0.25
    ansson
    -0.24
    åģļçļĦ
    -0.24
    POSITIVE LOGITS
    iling
    0.28
    pain
    0.27
    cbd
    0.27
    ova
    0.26
    STITUTE
    0.25
    stadt
    0.25
    uhan
    0.24
     thoáng
    0.24
     browse
    0.24
    xbd
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.