© 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. 30-TRANSCODER-HP
    7. 94891
    Prev
    Next
    INDEX
    Explanations

    book excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Addr
    -0.28
     cap
    -0.27
    -po
    -0.27
    odd
    -0.26
    âĬ¢
    -0.25
    edException
    -0.25
    ittel
    -0.24
    _po
    -0.24
    æĬ±
    -0.24
     Rout
    -0.24
    POSITIVE LOGITS
    (off
    0.24
    æĸĩç«łæĿ¥æºIJ
    0.24
     rein
    0.23
    -off
    0.23
     intra
    0.23
    躬
    0.23
    vertime
    0.23
    mmo
    0.23
     lul
    0.23
    æĸ¹åľĨ
    0.23
    Activations Density 0.103%

    No Known Activations