© 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. 30-TRANSCODER-HP
    7. 97100
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĨį说
    -0.28
    GPL
    -0.26
    åij¨æľ«
    -0.26
    dir
    -0.25
    UA
    -0.25
    åĨįæĿ¥
    -0.24
     Cornwall
    -0.24
    mere
    -0.23
    ishop
    -0.23
    lá
    -0.23
    POSITIVE LOGITS
    éĢĶä¸Ń
    0.27
    ette
    0.26
    éĻª
    0.26
    åĢ¾åIJij
    0.25
    é«ĺéĵģ
    0.25
    声
    0.25
    èĥĮæĻ¯
    0.24
    å°¤åħ¶
    0.23
    åIJ¸æĶ¶
    0.23
    hte
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.