© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6410
    Prev
    Next
    INDEX
    Explanations

    pollution

    np_max-act · gemini-2.0-flash
    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
     tern
    -0.27
     tục
    -0.26
    éĻIJãĤĬ
    -0.25
    å®ļäºĨ
    -0.24
     Thornton
    -0.23
     khách
    -0.23
    åıĹ访èĢħ
    -0.23
    icap
    -0.23
     {}↵
    -0.23
    зÑĭк
    -0.23
    POSITIVE LOGITS
     minded
    0.27
    åij¨åĽ´çļĦ
    0.25
    æ´ĩ
    0.25
    hurst
    0.24
    INESS
    0.24
    oks
    0.24
    çªĹå¤ĸ
    0.23
    éĻĦè¿ijçļĦ
    0.23
     nearby
    0.23
    ivas
    0.23
    Activations Density 0.929%

    No Known Activations