© 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. 29289
    Prev
    Next
    INDEX
    Explanations

    technical/medical contexts

    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
    uplicated
    -0.29
    ilateral
    -0.28
    èİ«åIJįåħ¶å¦Ļ
    -0.26
    moil
    -0.25
    adic
    -0.25
    溢
    -0.24
    .rd
    -0.24
    éĹ·
    -0.24
    .pp
    -0.24
     penny
    -0.24
    POSITIVE LOGITS
    ano
    0.30
     maps
    0.28
    ANO
    0.28
     invis
    0.27
    åħ°
    0.27
     Maps
    0.26
     Map
    0.26
    Map
    0.26
    主任
    0.25
    on
    0.25
    Activations Density 2.085%

    No Known Activations