© 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. 140677
    Prev
    Next
    INDEX
    Explanations

    code, technical instructions

    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
    è¿Ļæīįæĺ¯
    -0.40
    è¿ĺæĺ¯å¾Ī
    -0.37
    æīįæĺ¯
    -0.35
    preferred
    -0.32
     preferred
    -0.32
    åıĹ欢è¿İ
    -0.29
    æĽ´éĩįè¦ģ
    -0.28
    ãģ®æĸ¹ãģĮ
    -0.28
     best
    -0.28
    è¿ĺæĺ¯
    -0.28
    POSITIVE LOGITS
     mans
    0.27
    -vars
    0.26
    ä¸Ĭåįĩ
    0.25
    æŶéĹ´ä¸º
    0.25
    solete
    0.24
    设ç«ĭäºĨ
    0.24
     lö
    0.24
     wurden
    0.24
    å¤ķ
    0.23
    _vars
    0.23
    Activations Density 43.895%

    No Known Activations