© 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. 5268
    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
    èħ»
    -0.27
    ugin
    -0.27
    éĮ¢
    -0.26
    WARE
    -0.25
    ard
    -0.25
     MutableLiveData
    -0.25
    .idea
    -0.25
    åħį责声æĺİ
    -0.24
    åĪ°åºķ
    -0.24
    .dismiss
    -0.24
    POSITIVE LOGITS
    Usu
    0.28
    纶
    0.26
     cor
    0.25
    çļĦä½ľçĶ¨
    0.24
    .synthetic
    0.24
    çݯç»ķ
    0.24
    åIJĪæĪIJ
    0.24
    -conf
    0.24
    lse
    0.23
    ık
    0.23
    Activations Density 0.069%

    No Known Activations

    This feature has no known activations.