© 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. 4691
    Prev
    Next
    INDEX
    Explanations

    that

    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
    æľĢåIJİä¸Ģ次
    -0.25
    mort
    -0.25
    à¸ĵา
    -0.25
    rar
    -0.24
    æ¦ķ
    -0.23
    åĨĻä¸ĭ
    -0.23
     Gott
    -0.23
    ÐŁÐ¾Ð´ÑĢобнее
    -0.23
    urls
    -0.23
    æķ¢äºİ
    -0.23
    POSITIVE LOGITS
    mania
    0.30
     contrario
    0.27
    ään
    0.27
    åIJĮç±»
    0.27
    ovy
    0.24
    åı¦ä¸ĢåįĬ
    0.24
     Pty
    0.24
    æĸ¹åIJijçĽĺ
    0.24
    wald
    0.24
    å°±åı¯ä»¥äºĨ
    0.24
    Activations Density 0.261%

    No Known Activations