© 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. 129216
    Prev
    Next
    INDEX
    Explanations

    Times and dates

    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
    æĹ¥æľŁ
    -0.54
     dates
    -0.50
    æŶéĹ´
    -0.47
     calendars
    -0.45
    å®ļæŶ
    -0.45
    çļĦæŶéĹ´
    -0.44
     date
    -0.44
    dates
    -0.43
     clocks
    -0.43
    æŶéĹ´ä¸º
    -0.43
    POSITIVE LOGITS
    å¿ĥ缮ä¸Ń
    0.27
     marché
    0.26
    screen
    0.26
    SCREEN
    0.25
    è´ŁéĿ¢
    0.24
    llen
    0.24
    壮大
    0.24
    æ½¢
    0.24
    ialized
    0.24
    bara
    0.24
    Activations Density 35.286%

    No Known Activations