© 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. 62700
    Prev
    Next
    INDEX
    Explanations

    statements, events

    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
    chie
    -0.28
    idar
    -0.26
     inward
    -0.26
    å®ī举
    -0.26
     toward
    -0.25
    ï¸
    -0.25
    åIJijä¸Ĭ
    -0.23
     versa
    -0.23
     AN
    -0.23
     anonymously
    -0.23
    POSITIVE LOGITS
    æĹºåŃ£
    0.27
    ukt
    0.27
    _AXIS
    0.24
     admitting
    0.24
     oud
    0.24
    俾
    0.23
    è°ı
    0.23
    serter
    0.23
    ersistence
    0.23
    UGHT
    0.23
    Activations Density 6.813%

    No Known Activations