© 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. 142648
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    ä½İä½į
    -0.26
    SJ
    -0.26
    .lv
    -0.25
    lf
    -0.25
    sid
    -0.25
     alın
    -0.25
    æĸ½
    -0.24
     BOTH
    -0.24
    JM
    -0.24
    ASCII
    -0.24
    POSITIVE LOGITS
    éĺŁåijĺ们
    0.28
    纸ä¸Ĭ
    0.26
    .recycle
    0.25
    allel
    0.25
    aint
    0.24
     papers
    0.24
    åįģæĿ¡
    0.24
    keiten
    0.24
    å¸Ĥãģ®
    0.24
    iants
    0.24
    Activations Density 0.592%

    No Known Activations