© 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. 5859
    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
    brick
    -0.28
     Haram
    -0.25
     Ãĸn
    -0.25
    伧
    -0.25
    lyn
    -0.25
    /DD
    -0.25
    Ñģад
    -0.24
    vana
    -0.24
    å¼ĢçĿĢ
    -0.24
    igua
    -0.23
    POSITIVE LOGITS
    swer
    0.31
     afterwards
    0.26
     motive
    0.26
    çħ
    0.25
     puzz
    0.25
    åħ¨ä½ĵ
    0.24
    åºķ
    0.24
     tir
    0.23
    itar
    0.23
     repl
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.