© 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. 5339
    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
    otic
    -0.28
     cerco
    -0.27
    rett
    -0.26
    onna
    -0.26
    ä¼ģåĽ¾
    -0.25
     nastÄĻ
    -0.25
    庶
    -0.25
    spo
    -0.24
    夷
    -0.24
    itti
    -0.24
    POSITIVE LOGITS
    :<?
    0.27
    ä¹IJæĦı
    0.24
     Profiles
    0.24
    åıįè¿ĩæĿ¥
    0.24
     ↵            ↵
    0.24
    ÑģлÑĥÑĪ
    0.24
    è¿ĺæĺ¯å¾Ī
    0.24
     individually
    0.24
    :http
    0.24
    åIJ¬èµ·æĿ¥
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.