© 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. 20-TRANSCODER-HP
    7. 129188
    Prev
    Next
    INDEX
    Explanations

    Questions and expressions of intent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    coni
    -0.27
     sol
    -0.26
    ä¸ĩåħ¬éĩĮ
    -0.25
     '`
    -0.24
    moire
    -0.24
    éĻ¤
    -0.24
    chein
    -0.24
    æ¯ıä¸Ģ
    -0.24
    дов
    -0.23
     unknow
    -0.23
    POSITIVE LOGITS
    uja
    0.30
    ife
    0.27
    转身
    0.26
     optimal
    0.25
    Synopsis
    0.25
    ellular
    0.24
    TT
    0.24
    emy
    0.24
     Integral
    0.24
    人çĶŁçļĦ
    0.24
    Activations Density 15.149%

    No Known Activations