© 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. 5267
    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
    å±ķ
    -0.30
    reuse
    -0.30
    ·æĸ°
    -0.30
    æĸĩç«łæĿ¥æºIJ
    -0.26
    åįļ主
    -0.25
    bsub
    -0.25
    .grid
    -0.24
    ä¸Ĭæ¼Ķ
    -0.24
    amespace
    -0.23
    ixer
    -0.23
    POSITIVE LOGITS
     PropertyChanged
    0.25
    å¼¹
    0.25
     ded
    0.25
    åķ¡
    0.24
    méd
    0.24
    .ng
    0.24
    çªį
    0.23
    owered
    0.23
    omed
    0.22
    æģ¯
    0.22
    Activations Density 0.351%

    No Known Activations

    This feature has no known activations.