© 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. 5991
    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
    çĶ¨æĪ·çļĦ
    -0.29
    为ä¹ĭ
    -0.28
    Ļ¨
    -0.27
     cbd
    -0.26
    UserService
    -0.26
    &(
    -0.26
    _xpath
    -0.25
    让çĶ¨æĪ·
    -0.24
    UserController
    -0.24
    ä¸įæĪIJ
    -0.24
    POSITIVE LOGITS
    alli
    0.27
    erness
    0.27
    OT
    0.26
     chunk
    0.25
    åĸľ
    0.24
    ayah
    0.24
    Obj
    0.23
    era
    0.23
    oui
    0.23
     OpCode
    0.23
    Activations Density 1.715%

    No Known Activations

    This feature has no known activations.