© 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. 33-TRANSCODER-HP
    7. 54761
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    عار
    -0.27
    opy
    -0.27
    åĨ¥
    -0.26
    å¾®ç¬ij
    -0.25
     circ
    -0.24
     tượng
    -0.24
    mph
    -0.24
     crater
    -0.24
    çľĭä»ĸ
    -0.24
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.23
    POSITIVE LOGITS
    plash
    0.31
    顶å±Ĥ
    0.26
    QRS
    0.26
    bard
    0.25
    plied
    0.25
    graded
    0.25
    æĿ¡
    0.24
    rolled
    0.24
     plain
    0.24
     viz
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.