© 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. 108663
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Kou
    -0.28
    æĺµ
    -0.26
    ellung
    -0.26
    nova
    -0.25
    airo
    -0.25
    MU
    -0.24
    ouv
    -0.24
    zie
    -0.24
    å®Ļ
    -0.24
    .CopyTo
    -0.24
    POSITIVE LOGITS
    æĹ¥çĶµ
    0.30
    çłĮ
    0.29
    oes
    0.25
     ProductService
    0.25
     Staff
    0.25
    eturn
    0.25
    ariant
    0.25
    ystack
    0.24
     ras
    0.24
     Extensions
    0.24
    Activations Density 7.892%

    No Known Activations