© 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. 129228
    Prev
    Next
    INDEX
    Explanations

    Explanations and introductions

    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
    de
    -0.28
    compress
    -0.27
    æ²Ł
    -0.25
    urb
    -0.24
    å°ıæŶåīį
    -0.24
    ibr
    -0.24
    Im
    -0.23
    âī¥
    -0.23
    -FIRST
    -0.23
    .getChild
    -0.23
    POSITIVE LOGITS
    ishments
    0.28
    åĵij
    0.26
    ãģĹãģ¾ãģĨ
    0.25
     responseBody
    0.25
    è¿Ļä¹Īåģļ
    0.24
    omain
    0.24
    slice
    0.24
    licable
    0.24
    çķĶ
    0.24
    lers
    0.23
    Activations Density 4.120%

    No Known Activations