© 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. 20-TRANSCODER-HP
    7. 64798
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uild
    -0.27
    åĵģ
    -0.26
    大æĪĺ
    -0.26
    èģĶç½ij
    -0.25
    示èĮĥåĮº
    -0.25
    êµIJíĨµ
    -0.24
     accurately
    -0.24
    åĴĢ
    -0.24
    å¼Ħ
    -0.24
    skill
    -0.23
    POSITIVE LOGITS
    ä¸ĢåŃĹ
    0.28
    	Dim
    0.26
    èIJ
    0.26
    å«Įçĸij
    0.26
     momento
    0.26
    ยะ
    0.25
    ÑĤÑĮ
    0.25
    çīºçī²
    0.25
    æݧèĤ¡éĽĨåĽ¢
    0.24
    ennes
    0.24
    Activations Density 51.404%

    No Known Activations

    This feature has no known activations.