© 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. 131150
    Prev
    Next
    INDEX
    Explanations

    Ordering, lists, steps

    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
    ok
    -0.29
    InstanceState
    -0.27
    ä¾µ
    -0.26
     aras
    -0.26
    cies
    -0.26
    èĢĮä¸įæĺ¯
    -0.26
    -no
    -0.26
    ä½£
    -0.25
    åİĮ
    -0.25
    æĢģ
    -0.25
    POSITIVE LOGITS
    mesh
    0.30
     Either
    0.29
    hit
    0.29
    esson
    0.28
    surf
    0.27
     surf
    0.27
     suit
    0.26
     hit
    0.26
    &type
    0.26
    (Abstract
    0.25
    Activations Density 16.080%

    No Known Activations