© 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. 29292
    Prev
    Next
    INDEX
    Explanations

    human anatomy

    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
    inate
    -0.33
    uve
    -0.27
     bother
    -0.26
    åĿĽ
    -0.26
    æĸ°æĶ¿
    -0.25
     cer
    -0.25
    æĸ°çĶŁ
    -0.25
    åİ»åģļ
    -0.25
    æĸ°åħ´
    -0.25
     Cros
    -0.24
    POSITIVE LOGITS
    illé
    0.26
    trecht
    0.25
    otropic
    0.25
    åħĪ
    0.25
    uito
    0.25
    é¾Ł
    0.25
    edBy
    0.24
     (...)
    0.24
    ($__
    0.24
     Shake
    0.24
    Activations Density 2.182%

    No Known Activations