© 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. 19-TRANSCODER-HP
    7. 9484
    Prev
    Next
    INDEX
    Explanations

    thunderstorms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    mdl
    -0.24
    å¥Ĥ
    -0.24
    çIJĨæĢ§
    -0.24
     widest
    -0.23
    (-(
    -0.23
    (--
    -0.23
    åĿĬ
    -0.23
     glands
    -0.23
    Hierarchy
    -0.23
    ä¸įæľį
    -0.23
    POSITIVE LOGITS
    caret
    0.30
    ary
    0.27
    仪表
    0.27
    å¾Ī大
    0.24
    泡
    0.23
    herits
    0.23
    ìĭ¶
    0.23
    å°±è¦ģ
    0.23
     actu
    0.23
    powered
    0.22
    Activations Density 0.371%

    No Known Activations