© 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. 94895
    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
    oise
    -0.28
     Sloan
    -0.24
    pto
    -0.24
    æŃ£å¸¸ä½¿çĶ¨
    -0.24
    aim
    -0.24
    napshot
    -0.24
    .ft
    -0.23
    çļĦåŁºç¡Ģ
    -0.23
    .bed
    -0.23
    Magnitude
    -0.23
    POSITIVE LOGITS
    åIJĥè¿ĩ
    0.29
     incur
    0.27
    acet
    0.25
    çīĻ
    0.25
     american
    0.25
    åįĹéĥ¨
    0.24
    ä¸ī个æľĪ
    0.24
    ä¸ĥæľĪ
    0.24
    ega
    0.24
    æĻļæľŁ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.