© 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. 130951
    Prev
    Next
    INDEX
    Explanations

    Improvement, change, or action

    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
    稳å®ļçļĦ
    -0.28
    人ãģŁãģ¡
    -0.26
    æĪĸå°Ĩ
    -0.26
    人ãĢħ
    -0.25
    itchen
    -0.24
     motive
    -0.24
    æŀ¢
    -0.24
    algo
    -0.24
    inet
    -0.23
    çŀł
    -0.23
    POSITIVE LOGITS
    é½IJ
    0.32
    é»ĺ
    0.28
    ä¸įåĩº
    0.28
     Black
    0.26
     caramel
    0.26
    hus
    0.25
    kee
    0.25
    quez
    0.25
    ograd
    0.25
    é»ij
    0.25
    Activations Density 11.977%

    No Known Activations