© 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. 5425
    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
    LTE
    -0.31
    ç½ij讯
    -0.29
    说å¾Ĺ
    -0.25
    crawl
    -0.25
    èµ¢
    -0.24
     disguise
    -0.24
    æľīéĻIJ
    -0.24
    ç¦ģå¿Į
    -0.24
     Cousins
    -0.23
    variant
    -0.23
    POSITIVE LOGITS
    exterity
    0.27
    IGGER
    0.27
    engers
    0.25
    etri
    0.25
     sund
    0.25
    tml
    0.24
     observ
    0.24
    责任æĦŁ
    0.24
     steward
    0.24
    ToWorld
    0.24
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.