© 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. 5434
    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
    æĢ¨
    -0.26
    /MIT
    -0.25
    Spark
    -0.24
    SAFE
    -0.24
    ORN
    -0.24
    ssa
    -0.24
    èģĮ
    -0.23
     fflush
    -0.23
     cov
    -0.23
    亵
    -0.23
    POSITIVE LOGITS
    afari
    0.28
    inking
    0.27
    ewan
    0.26
    Trivia
    0.26
    trx
    0.26
    éĤ¸
    0.24
    ionario
    0.24
    èµ·æŃ¥
    0.24
    uled
    0.24
     arty
    0.24
    Activations Density 0.250%

    No Known Activations

    This feature has no known activations.