© 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. 17955
    Prev
    Next
    INDEX
    Explanations

    environmental/technical topics

    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
    addy
    -0.32
    æ±ł
    -0.27
    enne
    -0.26
    enze
    -0.24
    æĺ¯ä»¥
    -0.24
    anya
    -0.24
    beat
    -0.24
    æĵįä½ľ
    -0.23
    æĬĺ
    -0.23
    ENV
    -0.23
    POSITIVE LOGITS
     commission
    0.28
    Commission
    0.28
    å½¹
    0.27
    ewan
    0.27
    commission
    0.26
    insula
    0.26
     Commission
    0.26
    窿
    0.26
     Incorporated
    0.25
    ulk
    0.25
    Activations Density 0.002%

    No Known Activations