© 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. 130987
    Prev
    Next
    INDEX
    Explanations

    code/article excerpts

    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
    :numel
    -0.28
    buster
    -0.28
    IÃĵN
    -0.26
     arrivals
    -0.26
    ottle
    -0.26
    eyJ
    -0.25
    SUR
    -0.25
    usterity
    -0.25
     Tiá»ĥu
    -0.25
    -Ta
    -0.24
    POSITIVE LOGITS
    cern
    0.31
    åĽ½èµĦå§Ķ
    0.28
    ëĭ¹
    0.28
    Æ°á»Łng
    0.27
    æĸĩåĮĸåĴĮ
    0.27
    è¸Ŀ
    0.26
    管å§Ķä¼ļ
    0.25
    åĽ½éĻħ
    0.25
    éĵ¶
    0.25
    ich
    0.25
    Activations Density 74.219%

    No Known Activations