© 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. 108758
    Prev
    Next
    INDEX
    Explanations

    Advance, te

    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
    oldt
    -0.28
    æľīæĦı
    -0.27
    elts
    -0.26
    etten
    -0.25
     macro
    -0.25
     no
    -0.24
    llib
    -0.24
    URT
    -0.24
    ines
    -0.23
    endencies
    -0.23
    POSITIVE LOGITS
    antom
    0.27
    æİ¥åıĹ
    0.26
    platz
    0.26
     &(
    0.26
     Forever
    0.25
    NAL
    0.25
    crm
    0.25
     teg
    0.24
    ople
    0.24
    Forever
    0.24
    Activations Density 6.735%

    No Known Activations