© 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. 9438
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ies
    -0.32
    ocha
    -0.29
     бол
    -0.27
    rounded
    -0.27
    l
    -0.26
     suff
    -0.25
     brib
    -0.25
     sentiments
    -0.25
    asi
    -0.25
    并
    -0.25
    POSITIVE LOGITS
    inke
    0.28
    çĻ½çĻ½
    0.26
     groceries
    0.25
     Wyatt
    0.24
    forcer
    0.24
     Splash
    0.23
     egreg
    0.23
    .Access
    0.23
    ulary
    0.23
     india
    0.23
    Activations Density 0.060%

    No Known Activations