© 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. 106821
    Prev
    Next
    INDEX
    Explanations

    Code/HTML

    np_max-act · gemini-2.0-flash
    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
    æ·ĸ
    -0.29
     bindActionCreators
    -0.28
    ’Brien
    -0.26
    ä¸Ĭè°ĥ
    -0.24
    ünd
    -0.24
    å¼¹
    -0.24
    ä¸įè¿ľ
    -0.24
    å½Ī
    -0.24
    ä¸Ģäºĭ
    -0.23
    нÑĮ
    -0.23
    POSITIVE LOGITS
    ä»ĸåıĪ
    0.27
    åIJ«
    0.26
    hin
    0.25
    æĽ²
    0.25
    êµIJ
    0.25
    gradient
    0.24
    ocre
    0.24
     CROSS
    0.23
     properly
    0.23
    escaped
    0.23
    Activations Density 1.249%

    No Known Activations