© 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. 5178
    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
    æĮĩæłĩ
    -0.29
    æİĴéĻ¤
    -0.26
    æĽ´å¥½åľ°
    -0.24
    *
    -0.24
    ç¨ĭ度
    -0.24
    ï¼Ľ
    -0.24
    åŃĹ
    -0.24
     rằng
    -0.23
    .cloudflare
    -0.23
    Adapter
    -0.23
    POSITIVE LOGITS
    statt
    0.33
    è¶ħé«ĺ
    0.28
     lethal
    0.27
     repeating
    0.26
     mutually
    0.26
    åĽŀ头
    0.26
    åIJ¬å¾Ĺ
    0.26
    .jasper
    0.25
     unreal
    0.25
     escorted
    0.25
    Activations Density 0.132%

    No Known Activations

    This feature has no known activations.