© 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. 129232
    Prev
    Next
    INDEX
    Explanations

    Common sentence structure/code

    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
     Sac
    -0.27
    apat
    -0.26
    æľį
    -0.25
    ä¹ĭåIJİ
    -0.25
    aret
    -0.25
    éī´
    -0.25
    ades
    -0.25
    tod
    -0.25
    areth
    -0.25
    夺åıĸ
    -0.24
    POSITIVE LOGITS
    ä¸Ńåħ³
    0.27
    åģļ强
    0.27
     clutter
    0.25
    ç´Ĭ
    0.25
     départ
    0.25
    åľ°æłĩ
    0.25
    ÑĦон
    0.24
     Willis
    0.24
    Mes
    0.24
     affirm
    0.23
    Activations Density 79.536%

    No Known Activations