© 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. 64835
    Prev
    Next
    INDEX
    Explanations

    Statistics and numbers

    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
    继æī¿
    -0.27
     inherits
    -0.26
     inherit
    -0.26
    eyJ
    -0.26
    inherit
    -0.26
    æģ¢
    -0.26
    ————————
    -0.26
    imity
    -0.26
     Joined
    -0.25
     setType
    -0.24
    POSITIVE LOGITS
    åİ¢
    0.30
    stock
    0.28
    离å¼Ģ
    0.28
    ror
    0.28
    离å¼ĢäºĨ
    0.28
    çıĪ
    0.27
    Prototype
    0.27
    å¸ĪåħĦ
    0.27
    箧
    0.26
    oland
    0.26
    Activations Density 3.844%

    No Known Activations