© 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. 32-TRANSCODER-HP
    7. 40974
    Prev
    Next
    INDEX
    Explanations

    Medical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     hy
    -0.34
     Hy
    -0.28
    Hy
    -0.28
    phe
    -0.28
    æĪ·
    -0.28
    hy
    -0.27
     Morm
    -0.27
    æĪ¶
    -0.27
    htable
    -0.27
    HY
    -0.26
    POSITIVE LOGITS
    tu
    0.31
    scrollTop
    0.30
    TI
    0.28
    loth
    0.28
    æīĺ
    0.28
     st
    0.28
    åĽ¾ä¸º
    0.27
    æĤłæĤł
    0.27
     GT
    0.26
    itt
    0.26
    Activations Density 0.009%

    No Known Activations