© 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. 64608
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    åĪ¹éĤ£
    -0.29
    å¡ijæĸĻ
    -0.28
    Later
    -0.28
    .shtml
    -0.27
    åŃĺ
    -0.26
    éľīç´ł
    -0.26
     octave
    -0.26
    èī¯
    -0.25
    第ä¸ĢæĿ¡
    -0.25
    ulos
    -0.25
    POSITIVE LOGITS
     broken
    0.28
    onio
    0.28
    ilan
    0.27
     Broken
    0.26
     fluctuations
    0.26
    uffed
    0.26
    broken
    0.26
    scan
    0.25
    äm
    0.25
     fl
    0.25
    Activations Density 8.571%

    No Known Activations