© 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. 44205
    Prev
    Next
    INDEX
    Explanations

    Source code

    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
    etu
    -0.28
    ä¼ļè®®
    -0.28
     Conference
    -0.26
    UILTIN
    -0.26
    ides
    -0.26
     conference
    -0.26
     conferences
    -0.26
     Separator
    -0.25
     confirm
    -0.25
    害
    -0.25
    POSITIVE LOGITS
     Pent
    0.27
    ValueCollection
    0.26
    Autor
    0.26
    tg
    0.25
    .aw
    0.25
     bá»ı
    0.24
    oram
    0.24
    åŁº
    0.24
    iez
    0.24
     oblig
    0.24
    Activations Density 0.006%

    No Known Activations