© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    utters
    -0.25
    eva
    -0.25
    idden
    -0.25
    ees
    -0.24
    ee
    -0.24
     Arlington
    -0.24
    bsp
    -0.24
    宣åijĬ
    -0.23
    .nih
    -0.23
    phil
    -0.23
    POSITIVE LOGITS
    åģļå·¥
    0.26
    que
    0.26
     gram
    0.26
    grams
    0.24
    åĮĸèĤ¥
    0.24
    æł·
    0.24
    icate
    0.24
    æł·çļĦ
    0.24
    ote
    0.23
    pecially
    0.23
    Activations Density 0.074%

    No Known Activations

    This feature has no known activations.