© 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. 129118
    Prev
    Next
    INDEX
    Explanations

    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
    verse
    -0.28
    åĬ¡
    -0.26
    pei
    -0.25
     PY
    -0.24
    æĸ°äº¬
    -0.24
     rate
    -0.24
    _ber
    -0.24
    å±ħæ°ij
    -0.24
     pair
    -0.24
     Georg
    -0.24
    POSITIVE LOGITS
    çłĶ究æĪIJæŀľ
    0.29
    침
    0.28
     Folk
    0.26
    egrator
    0.26
    ernel
    0.25
    åĵ©
    0.25
    ä»İä¸Ń
    0.25
    ç§ģãģĮ
    0.25
    è¯ļ
    0.25
    ifter
    0.24
    Activations Density 7.850%

    No Known Activations