© 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. 5030
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    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
    æ»ij
    -0.28
    æ³Ľ
    -0.28
    éĿ
    -0.27
    brit
    -0.26
     onLoad
    -0.26
    éĥ½æľīçĿĢ
    -0.25
    EDI
    -0.25
    åħ·æľīä¸Ģå®ļ
    -0.24
    olid
    -0.24
    bro
    -0.24
    POSITIVE LOGITS
    è¿ĩç¨ĭä¸Ń
    0.28
     exh
    0.28
     expulsion
    0.26
    ä¸įåı¯ä»¥
    0.26
    å®ŀè·µä¸Ń
    0.26
    è¿ĩç¨ĭ
    0.25
    æĻļé¤IJ
    0.25
     darf
    0.24
    -bo
    0.24
     —↵↵
    0.24
    Activations Density 0.048%

    No Known Activations