© 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. 130808
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.32
    lesh
    -0.30
    æĭĽèģĺ
    -0.26
    .fil
    -0.25
    ewire
    -0.25
     hires
    -0.24
    ç½Ł
    -0.24
    [in
    -0.24
    еÑĢж
    -0.23
     flo
    -0.23
    POSITIVE LOGITS
    çĽ²çĽ®
    0.28
    asel
    0.26
    Äħż
    0.26
     symp
    0.25
    åİ»è¿ĩ
    0.24
    ullen
    0.24
    erve
    0.24
    omo
    0.24
    otope
    0.24
    омеÑĢ
    0.23
    Activations Density 5.367%

    No Known Activations

    This feature has no known activations.