© 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. 106790
    Prev
    Next
    INDEX
    Explanations

    constantly

    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
    ä¸ĬæĿ¥
    -0.34
    ä¸Ģ页
    -0.29
    oliberal
    -0.27
    æĮīä¸ĭ
    -0.27
    ibaba
    -0.25
     upward
    -0.25
    ä¸įä¸ĭ
    -0.25
     whole
    -0.25
    人åĿĩ
    -0.25
    ä¸ĬäºĨ
    -0.24
    POSITIVE LOGITS
    ATT
    0.29
     fed
    0.29
    åļı
    0.28
     Ass
    0.27
    dom
    0.27
     born
    0.26
    Ass
    0.26
     fury
    0.26
    illion
    0.25
     sworn
    0.25
    Activations Density 43.507%

    No Known Activations