© 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. 31-TRANSCODER-HP
    7. 17924
    Prev
    Next
    INDEX
    Explanations

    Code and special markup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    erus
    -0.31
    泡
    -0.28
    æĻĭ
    -0.27
    ึ
    -0.25
    æĸIJ
    -0.25
    [text
    -0.25
    è¨Ģ
    -0.25
    anden
    -0.25
    æĽ´æĸ°
    -0.25
    ialis
    -0.24
    POSITIVE LOGITS
    OAD
    0.33
     orthogonal
    0.28
    R
    0.27
    ORITY
    0.25
     curves
    0.24
    ORA
    0.24
    hma
    0.24
    hm
    0.24
    -clear
    0.24
    IDA
    0.23
    Activations Density 0.050%

    No Known Activations