© 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. 9686
    Prev
    Next
    INDEX
    Explanations

    A

    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
    orthand
    -0.27
    ForRow
    -0.25
    ODY
    -0.25
     tumble
    -0.25
    ser
    -0.24
     incontro
    -0.24
    ghi
    -0.24
    èĪĮ头
    -0.24
    wizard
    -0.24
     анг
    -0.24
    POSITIVE LOGITS
    大家
    0.31
    大家éĥ½åľ¨
    0.27
    ained
    0.25
     News
    0.24
    ipp
    0.24
    else
    0.24
    other
    0.23
    Next
    0.23
    -
    0.23
    æĸ¼æĺ¯
    0.23
    Activations Density 0.015%

    No Known Activations