© 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. 6328
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.28
     vad
    -0.26
    credited
    -0.26
    è§Ħéģ¿
    -0.26
    åįıä¼ļä¼ļåijĺ
    -0.25
     creeping
    -0.25
    åºĵ
    -0.24
     Mey
    -0.23
    _SAFE
    -0.23
    æķĻåŃ¦è´¨éĩı
    -0.23
    POSITIVE LOGITS
     lif
    0.29
    olith
    0.24
    çīĽå¸Ĥ
    0.24
    theon
    0.24
     smooth
    0.24
     imp
    0.24
     solder
    0.23
    aspect
    0.23
    å¹³
    0.23
     smoothly
    0.23
    Activations Density 0.804%

    No Known Activations