© 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. 5763
    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
    ukes
    -0.30
    ¢åįķ
    -0.26
    jump
    -0.26
    enate
    -0.25
    jas
    -0.24
     redirectTo
    -0.23
    communic
    -0.23
    Checkout
    -0.23
    æľºéģĩ
    -0.23
    gı
    -0.23
    POSITIVE LOGITS
    -↵
    0.26
    åIJĿ
    0.26
    eral
    0.26
     operations
    0.25
    çļĦçľ¼åħī
    0.25
    åIJĪ
    0.25
    ama
    0.25
     entren
    0.24
    ÑĤон
    0.24
    lat
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.