© 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. 95126
    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
    mgr
    -0.28
    éĺIJæĺİ
    -0.26
    ä¸Ī
    -0.26
    è¯Ŀ说
    -0.26
    Mgr
    -0.25
    娲
    -0.25
     obe
    -0.24
    hover
    -0.24
    è´Łè´£åIJĮå¿Ĺ
    -0.24
     AUG
    -0.24
    POSITIVE LOGITS
    讫
    0.25
    å²ģ以ä¸ĭ
    0.25
     Minist
    0.25
     Agencies
    0.25
    ä½ĸ
    0.24
    æľĶ
    0.24
    æ¶ķ
    0.24
    aca
    0.24
     floor
    0.24
    身躯
    0.23
    Activations Density 0.886%

    No Known Activations

    This feature has no known activations.