© 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. 19-TRANSCODER-HP
    7. 9659
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     BaseService
    -0.25
    crawl
    -0.25
    .ForEach
    -0.25
    åıįå¤į
    -0.24
    éŃģ
    -0.24
    ttl
    -0.24
    åĸĺ
    -0.24
    åĺ±
    -0.23
     TestCase
    -0.23
    atro
    -0.23
    POSITIVE LOGITS
    Deep
    0.25
    èĥ½åĬĽå¼º
    0.25
     answer
    0.25
    æ·±åħ¥æİ¨è¿Ľ
    0.24
    è¯ī讼
    0.24
     Support
    0.24
     anim
    0.24
    answer
    0.23
    æİ¥åıĹ
    0.23
    æľºéģĩ
    0.23
    Activations Density 0.028%

    No Known Activations