© 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. 140757
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    asz
    -0.28
     favoured
    -0.25
    -Oct
    -0.25
    heed
    -0.25
    èµł
    -0.24
    ÏĮ
    -0.24
    ,bool
    -0.24
    ØŃÙĤÙĤ
    -0.23
    /classes
    -0.23
    êu
    -0.23
    POSITIVE LOGITS
    æĪı
    0.27
    æ´ª
    0.26
    .cgi
    0.26
    å°¤åħ¶æĺ¯åľ¨
    0.25
    erdale
    0.25
    ãģĦãĤĦ
    0.24
    æĭĬ
    0.23
     instead
    0.23
    ỳ
    0.23
    æľīéĻIJ责任
    0.23
    Activations Density 88.471%

    No Known Activations