© 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. 129154
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    mue
    -0.30
    udas
    -0.27
    æ²Ł
    -0.26
     reactive
    -0.26
    à¸Ńล
    -0.25
    ÄĻ
    -0.25
    åħ³æ³¨åº¦
    -0.24
    /javascript
    -0.24
    \u
    -0.24
    æIJĵ
    -0.24
    POSITIVE LOGITS
    è¨ĵ
    0.29
    è®Ń
    0.28
     Herc
    0.27
     Identified
    0.25
    åķĨ
    0.25
    å·²å®ĮæĪIJ
    0.25
    çĶŁçī©ç§ijæĬĢ
    0.24
     Bi
    0.24
     zie
    0.24
    |[
    0.24
    Activations Density 1.248%

    No Known Activations