© 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. 30-TRANSCODER-HP
    7. 96888
    Prev
    Next
    INDEX
    Explanations

    brought

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -in
    -0.35
    ä¸ĭåİ»
    -0.31
     harvested
    -0.29
     abolished
    -0.28
     ridden
    -0.27
     pinned
    -0.26
     neglected
    -0.26
    éĽ¢
    -0.26
    -signed
    -0.26
     generated
    -0.26
    POSITIVE LOGITS
     bring
    0.45
     Bringing
    0.39
     bringing
    0.38
    bringing
    0.37
     brings
    0.37
    Bring
    0.36
     Bring
    0.35
    带
    0.34
    带æĿ¥
    0.32
    bring
    0.32
    Activations Density 0.784%

    No Known Activations