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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5306
    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
     Volk
    -0.28
    iler
    -0.27
    Placeholder
    -0.27
    ERS
    -0.27
    è¿Ļä¹Ī
    -0.25
    è´Łèį·
    -0.24
    à¹Ĥà¸Ķ
    -0.24
    ensch
    -0.23
     oppon
    -0.23
    estr
    -0.23
    POSITIVE LOGITS
    åŃIJ女
    0.27
    arrant
    0.27
    ences
    0.27
    /mit
    0.27
    enced
    0.26
    belie
    0.26
    ä»»ä½ķå½¢å¼ı
    0.25
    åħ¼
    0.25
    "".
    0.24
    åĽłä¸ºä»ĸ们
    0.24
    Activations Density 0.024%

    No Known Activations

    This feature has no known activations.