© 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. 9-TRANSCODER-HP
    7. 30414
    Prev
    Next
    INDEX
    Explanations

    medical imaging/radiology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ticket
    -0.28
    -rays
    -0.28
     radioactive
    -0.28
    çľ¯
    -0.27
    æĶ¾å°Ħ
    -0.27
    ivas
    -0.27
    æī«æıı
    -0.27
     photographic
    -0.26
    ipple
    -0.26
    çŃĽæŁ¥
    -0.26
    POSITIVE LOGITS
    bef
    0.28
    -kit
    0.26
    åħij
    0.25
    åħ¥åºĵ
    0.25
    马æĭī
    0.25
    廪
    0.24
     AUTHORS
    0.24
     planted
    0.24
    .SaveChanges
    0.24
    å·¥ç¨ĭæĬĢæľ¯
    0.24
    Activations Density 0.813%

    No Known Activations