© 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. 5734
    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
    åIJij社ä¼ļ
    -0.29
    :w
    -0.26
    :left
    -0.25
    :m
    -0.25
    /md
    -0.24
    :l
    -0.24
     breed
    -0.24
     inspired
    -0.24
    å¼¥
    -0.24
     diff
    -0.23
    POSITIVE LOGITS
    topic
    0.31
     Topic
    0.30
    igung
    0.29
    åľ¨è¿Ļæĸ¹éĿ¢
    0.27
     Subjects
    0.27
     könnt
    0.27
    Creature
    0.26
    .Subject
    0.26
    HEN
    0.26
     Subject
    0.25
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.