© 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. 9611
    Prev
    Next
    INDEX
    Explanations

    Article snippets

    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
    istar
    -0.29
    ilon
    -0.27
    odule
    -0.27
    家åĸ»
    -0.25
    lood
    -0.25
     borç
    -0.25
    alous
    -0.24
     {{{
    -0.24
     ruling
    -0.24
    utura
    -0.23
    POSITIVE LOGITS
    æĬ¼
    0.30
    ượng
    0.28
    plug
    0.26
    ðŁijĪ
    0.26
    éļį
    0.25
    åħ¬å¼Ģ
    0.24
    æįı
    0.23
    /sl
    0.23
    å¥ĩ
    0.23
    ager
    0.23
    Activations Density 0.058%

    No Known Activations