© 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. 62549
    Prev
    Next
    INDEX
    Explanations

    academic publications

    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
     note
    -0.27
    note
    -0.26
    æijĴ
    -0.25
     NOTE
    -0.25
    levator
    -0.24
     Note
    -0.24
    è®°
    -0.24
    elter
    -0.24
    -native
    -0.23
    .note
    -0.23
    POSITIVE LOGITS
    riba
    0.26
    åŃ¦æł¡çļĦ
    0.26
     "'"
    0.25
    odesk
    0.25
    ä¸ĭ游
    0.25
    鼯
    0.25
    amation
    0.25
    minster
    0.24
    ä¸Ĭ游
    0.24
    级åĪ«çļĦ
    0.24
    Activations Density 7.830%

    No Known Activations