© 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. 62709
    Prev
    Next
    INDEX
    Explanations

    Technical questions and issues

    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
    å¾Ĵ
    -0.30
     Emblem
    -0.28
    edia
    -0.27
    luet
    -0.27
     recip
    -0.26
     Rogue
    -0.25
    ีย
    -0.24
    åķ¸
    -0.24
    ipe
    -0.24
    çķ«
    -0.24
    POSITIVE LOGITS
    sole
    0.27
    vac
    0.27
    .pan
    0.26
    箸
    0.25
    ãģªãĤī
    0.24
    以ä¸Ĭãģ®
    0.24
    .IsNullOrWhiteSpace
    0.23
    绾
    0.23
    Pan
    0.23
    ografÃŃa
    0.23
    Activations Density 0.768%

    No Known Activations