© 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. 129153
    Prev
    Next
    INDEX
    Explanations

    actions/processes

    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
    æĢ»çĽij
    -0.27
    æŶéĹ´ä¸º
    -0.25
    LinkId
    -0.25
    æĮĩçĶ²
    -0.24
    unky
    -0.23
    åĬŀ好
    -0.23
    éĩı
    -0.23
    åĪĨå¸ĥåľ¨
    -0.23
    {i
    -0.23
    <quote
    -0.22
    POSITIVE LOGITS
    ighbours
    0.26
    cd
    0.25
    å°ıæŶåīį
    0.25
    bd
    0.24
    ç
    0.24
    身ä¸Ĭ
    0.23
    chn
    0.23
    릴
    0.23
     lo
    0.23
    ref
    0.23
    Activations Density 39.334%

    No Known Activations