© 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. 129004
    Prev
    Next
    INDEX
    Explanations

    technical reporting

    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
     posts
    -0.29
     Posts
    -0.28
    iras
    -0.28
    riz
    -0.28
     overlaps
    -0.27
    [/
    -0.26
    éĩį
    -0.26
    debit
    -0.25
    uples
    -0.25
     Tip
    -0.25
    POSITIVE LOGITS
    eled
    0.26
    wing
    0.26
    /cgi
    0.25
     Scrap
    0.25
    ockey
    0.25
    Russian
    0.24
    udget
    0.24
    oplay
    0.23
    _conditions
    0.23
     Justi
    0.23
    Activations Density 0.283%

    No Known Activations