© 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. 64845
    Prev
    Next
    INDEX
    Explanations

    Formal/Informative writing style

    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
    omen
    -0.27
    å¼ĢéĢļ
    -0.25
    è¿ĩ
    -0.25
    ovah
    -0.25
    asmine
    -0.25
    openh
    -0.24
     xuân
    -0.24
    æĺ¥æĻļ
    -0.24
    mix
    -0.23
    illis
    -0.23
    POSITIVE LOGITS
     Ada
    0.28
    åħij
    0.26
    PHA
    0.26
    éĥ½ä¼ļæľī
    0.25
    Ada
    0.25
     crawl
    0.25
    uvw
    0.25
     brag
    0.24
    Tho
    0.24
    ibal
    0.24
    Activations Density 4.657%

    No Known Activations