© 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. 140725
    Prev
    Next
    INDEX
    Explanations

    Code and file metadata

    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
     etiquette
    -0.29
    æĸĩä½ĵ
    -0.29
    eli
    -0.27
     Flake
    -0.26
    ä»ħä¾ĽåıĤèĢĥ
    -0.26
    lesi
    -0.25
    _slow
    -0.25
    isches
    -0.25
    æľī害
    -0.24
    hek
    -0.24
    POSITIVE LOGITS
    stick
    0.28
    andr
    0.27
     Modern
    0.26
     modern
    0.26
    Modern
    0.25
    modern
    0.25
    紧缺
    0.25
     Greater
    0.24
    creens
    0.24
    lad
    0.24
    Activations Density 1.545%

    No Known Activations