© 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. 96952
    Prev
    Next
    INDEX
    Explanations

    Measurement/Comparison

    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
    ingo
    -0.30
    igans
    -0.27
    sey
    -0.26
     responseBody
    -0.26
    ivor
    -0.25
    soup
    -0.25
    åģļçļĦ
    -0.25
    omics
    -0.25
    FREE
    -0.25
    onald
    -0.25
    POSITIVE LOGITS
     disproportion
    0.35
    éĻIJ度
    0.31
     ten
    0.29
    åħ·æľīä¸Ģå®ļ
    0.28
    æĬij
    0.28
     nan
    0.27
    äºĨä¸Ģæī¹
    0.27
     large
    0.27
     existence
    0.27
     larger
    0.27
    Activations Density 0.884%

    No Known Activations