© 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. 19-TRANSCODER-HP
    7. 9447
    Prev
    Next
    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    sdale
    -0.31
    licting
    -0.28
    åIJĪä¸Ģ
    -0.27
    ourses
    -0.26
    /dc
    -0.26
    opian
    -0.24
    otive
    -0.24
     concurrent
    -0.24
    aggable
    -0.24
    /Base
    -0.24
    POSITIVE LOGITS
    åIJįå½ķ
    0.29
    æĬķèµĦé¡¹çĽ®
    0.26
    Į¨
    0.26
    çļĦæĬķèµĦ
    0.25
     wcs
    0.24
    è°İè¨Ģ
    0.24
    ×IJ×Ķ
    0.24
    ä¾Ľæ±Ĥ
    0.24
    é¨Ļ
    0.24
     instructions
    0.23
    Activations Density 0.004%

    No Known Activations