© 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. 129100
    Prev
    Next
    INDEX
    Explanations

    cut

    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
    Ever
    -0.25
     ped
    -0.24
      ↵  ↵
    -0.24
    perate
    -0.24
    istle
    -0.24
     Sox
    -0.23
     EVER
    -0.23
     Weaver
    -0.23
     rains
    -0.23
    illin
    -0.23
    POSITIVE LOGITS
    ä¸įä¼ļåĨį
    0.27
    éªĬ
    0.26
     vintage
    0.25
     Modeling
    0.25
    å¿łè¯ļ
    0.25
    å¤ļä½Ļ
    0.24
    -hole
    0.24
    inges
    0.24
    äºĶæĺŁ
    0.24
    ä»£æĽ¿
    0.24
    Activations Density 0.818%

    No Known Activations