© 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. 142591
    Prev
    Next
    INDEX
    Explanations

    Plasma/serum

    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
    ijo
    -0.27
     Nice
    -0.27
     Neb
    -0.25
    .local
    -0.24
    benh
    -0.24
     Patrol
    -0.24
    ãĥ¬ãĤ¹ãĥĪ
    -0.24
    lections
    -0.24
    biz
    -0.24
    angs
    -0.23
    POSITIVE LOGITS
     wake
    0.25
    ä¸ĢåĪĩéĥ½æĺ¯
    0.25
    .processor
    0.25
    åĭĴ
    0.25
    pirit
    0.24
     soup
    0.24
     tonic
    0.23
    zed
    0.23
    ç½ij讯
    0.23
    ucas
    0.23
    Activations Density 15.105%

    No Known Activations