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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4736
    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
    å¼ĺ
    -0.30
    æµĵ缩
    -0.29
     condensed
    -0.25
    è§Ī
    -0.24
    çݯå¢ĥä¸ĭ
    -0.24
    ROL
    -0.24
    ajan
    -0.24
    çļĦæĸĩç«ł
    -0.23
    å¿Į
    -0.23
    odem
    -0.23
    POSITIVE LOGITS
    <quote
    0.30
    InSection
    0.27
    mouth
    0.27
    iego
    0.27
    forme
    0.26
    gle
    0.26
    icts
    0.26
    rn
    0.26
     mouths
    0.25
    ä¹Łè®¸
    0.25
    Activations Density 0.101%

    No Known Activations

    This feature has no known activations.