© 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. 31-TRANSCODER-HP
    7. 19823
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    oust
    -0.28
    âĪ¼
    -0.26
    éĹª
    -0.25
     Caul
    -0.25
    lder
    -0.25
     identity
    -0.24
    following
    -0.24
    åĪĺæµ·
    -0.24
    ~~~~~~~~~~~~~~~~
    -0.24
    irst
    -0.24
    POSITIVE LOGITS
     org
    0.28
    zen
    0.27
     organ
    0.27
    INARY
    0.27
    Bias
    0.26
    ä¸ĵ项
    0.26
    æĿ¯
    0.26
    åĹij
    0.25
    纪å½ķ
    0.25
    org
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.