© 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. 64808
    Prev
    Next
    INDEX
    Explanations

    if

    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
     hog
    -0.27
    ä¸īæĿ¡
    -0.26
    msgid
    -0.25
     Ãĸz
    -0.25
    çi
    -0.25
    è°ĥè¯ķ
    -0.25
    æĮ¨
    -0.24
    çīĮ
    -0.24
    æĿĸ
    -0.24
    inan
    -0.24
    POSITIVE LOGITS
    æŀľ
    0.27
    cu
    0.26
     inconvenient
    0.26
     intervals
    0.26
    obra
    0.26
    ottage
    0.25
    !--
    0.24
    rightness
    0.24
    ormal
    0.24
    etween
    0.24
    Activations Density 35.964%

    No Known Activations