© 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. 142713
    Prev
    Next
    INDEX
    Explanations

    :N

    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
    伯
    -0.27
     ro
    -0.26
     oper
    -0.25
     Income
    -0.25
     gr
    -0.24
     writ
    -0.24
    acted
    -0.24
     se
    -0.24
     sw
    -0.24
    à¸Ħร
    -0.24
    POSITIVE LOGITS
    yı
    0.27
    ffect
    0.26
    &p
    0.25
    Describe
    0.25
    dio
    0.25
    alyze
    0.25
    çĶŁäº§çļĦ
    0.25
    RULE
    0.24
    CGSize
    0.24
    ivist
    0.24
    Activations Density 14.323%

    No Known Activations