© 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. 129243
    Prev
    Next
    INDEX
    Explanations

    Legal/Government/Societal issues

    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
    ruise
    -0.27
    yms
    -0.26
     nues
    -0.26
    hta
    -0.24
     rollout
    -0.24
     skal
    -0.23
    latable
    -0.23
    traî
    -0.23
    laus
    -0.23
    çł´
    -0.23
    POSITIVE LOGITS
    -and
    0.65
    _and
    0.62
     &
    0.62
    &
    0.61
    And
    0.54
     And
    0.49
    &↵
    0.49
     &↵
    0.49
    _AND
    0.47
    &P
    0.47
    Activations Density 80.685%

    No Known Activations