© 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. 131127
    Prev
    Next
    INDEX
    Explanations

    arts

    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
    chers
    -0.26
     resonate
    -0.25
    ersed
    -0.25
    éĻIJãĤĬ
    -0.25
     Denis
    -0.24
    herits
    -0.24
     SHARES
    -0.24
    nis
    -0.24
    elli
    -0.24
    asley
    -0.23
    POSITIVE LOGITS
    éĢĤ
    0.28
    身
    0.27
    åĮĸè¿Ľç¨ĭ
    0.26
     epit
    0.26
    .sav
    0.26
    æľ´ç´ł
    0.26
    æĪijä¸į
    0.25
    é»ijçĻ½
    0.25
    æİī
    0.25
    caff
    0.25
    Activations Density 4.777%

    No Known Activations