© 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. 140605
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     (*)(
    -0.26
     Flickr
    -0.25
    acho
    -0.25
     Tribune
    -0.24
    è°ĥæݧ
    -0.24
    testimonial
    -0.24
    ãĥ¬ãĥĵ
    -0.23
    "".
    -0.23
    phia
    -0.23
     -.
    -0.23
    POSITIVE LOGITS
    oux
    0.28
    outh
    0.28
    .units
    0.26
    chine
    0.26
     gr
    0.26
    åĽŀ头
    0.25
    owo
    0.25
    off
    0.25
    ho
    0.24
    çļĦ身影
    0.24
    Activations Density 1.503%

    No Known Activations