© 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. 129165
    Prev
    Next
    INDEX
    Explanations

    Nationalities and Operating Systems

    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
    LOSE
    -0.27
    ç¯ĩç«ł
    -0.25
     DIE
    -0.25
     Triple
    -0.24
     Tou
    -0.24
    ä»ħ代表
    -0.23
    çļĦ缮åħī
    -0.23
     Tri
    -0.23
    çŃī级
    -0.23
     vale
    -0.23
    POSITIVE LOGITS
    Poll
    0.27
    çªį
    0.27
    canvas
    0.27
    bens
    0.26
    eled
    0.25
    -assets
    0.25
    äs
    0.25
    olic
    0.25
    bery
    0.25
    anky
    0.24
    Activations Density 29.206%

    No Known Activations