© 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. 6043
    Prev
    Next
    INDEX
    Explanations

    by

    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
    éĽĨåĽ¢èĤ¡ä»½
    -0.25
     worried
    -0.25
    ↵↵    ↵
    -0.24
     Zust
    -0.24
    Cisco
    -0.24
    regs
    -0.23
    饿
    -0.23
    ZW
    -0.23
    fre
    -0.23
    éĢIJ
    -0.23
    POSITIVE LOGITS
     sÃłng
    0.28
     FAG
    0.27
    yle
    0.26
    éĤ¸
    0.25
    bpp
    0.25
    éĢĻ樣
    0.25
    /op
    0.24
     dÃłng
    0.23
    dge
    0.23
     mater
    0.23
    Activations Density 0.023%

    No Known Activations