© 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. 140705
    Prev
    Next
    INDEX
    Explanations

    Beginning of a passage

    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
     æĪĸ
    -0.27
    æĪĸèĢħæĺ¯
    -0.26
    æĪĸæĺ¯
    -0.26
    ueue
    -0.26
     Pyongyang
    -0.26
    DSL
    -0.25
    erea
    -0.25
     overlays
    -0.25
    æĪĸèĢħ
    -0.23
    ä¿Ŀç½Ĺ
    -0.23
    POSITIVE LOGITS
    cha
    0.31
    Lens
    0.28
    gn
    0.26
    Tre
    0.26
    æ¯ı个人éĥ½
    0.26
     closed
    0.26
    horn
    0.25
    sc
    0.25
    æ²Ļ
    0.25
    èªĵ
    0.25
    Activations Density 30.570%

    No Known Activations