© 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. 6398
    Prev
    Next
    INDEX
    Explanations

    code-related

    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
    byss
    -0.28
     ende
    -0.28
    çĤ¯
    -0.27
    头éĥ¨
    -0.26
    rogate
    -0.26
    å¤ĸå¥Ĺ
    -0.26
    å¢ŀåĬłåĢ¼
    -0.25
    rieved
    -0.25
    åªļ
    -0.25
    prit
    -0.25
    POSITIVE LOGITS
     Booth
    0.27
     effectively
    0.26
    Recommend
    0.26
    ç´ł
    0.25
    éĤ£ä»½
    0.24
     Theodore
    0.24
     virtually
    0.24
     booth
    0.24
     Reason
    0.23
    ÙĦس
    0.23
    Activations Density 0.792%

    No Known Activations