© 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. 44121
    Prev
    Next
    INDEX
    Explanations

    liver or kidney

    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
    COND
    -0.28
    ennes
    -0.27
     Cond
    -0.27
     cond
    -0.27
    -cond
    -0.26
     Half
    -0.26
    .Highlight
    -0.25
    á»ijt
    -0.25
    端
    -0.25
    лег
    -0.25
    POSITIVE LOGITS
    ç½Ĺ马
    0.30
    å£ģ
    0.29
     vere
    0.27
    wort
    0.26
     pathological
    0.26
    éĤ£ä»½
    0.26
    peating
    0.25
    former
    0.25
    åĽ½åĬ¡éĻ¢
    0.25
    è¿Ļ份
    0.25
    Activations Density 0.011%

    No Known Activations