© 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. 140824
    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
    æĢĿãģĨ
    -0.26
    è¾Ĺ转
    -0.25
     cerco
    -0.25
    ä¸ĩæĪ·
    -0.25
    æķ´å½¢
    -0.24
    yk
    -0.24
    伺
    -0.24
    ç²¾ç¥ŀ
    -0.23
    rug
    -0.23
     concatenated
    -0.23
    POSITIVE LOGITS
    ucher
    0.25
    çļĦç¨ĭ度
    0.25
    elor
    0.25
    leans
    0.24
    uch
    0.24
    æłĮ
    0.24
    _than
    0.23
    æĤ«
    0.23
    LEV
    0.23
    æľªæĪIJ
    0.23
    Activations Density 8.578%

    No Known Activations

    This feature has no known activations.