© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30472
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    __;↵
    -0.28
    å¾ģ
    -0.27
    éĢĴ
    -0.27
    æīİæł¹
    -0.26
    AGR
    -0.26
    __↵
    -0.26
    å¾µ
    -0.26
     ass
    -0.25
    åĬªåĬĽ
    -0.24
    __);↵
    -0.24
    POSITIVE LOGITS
    æĸĩåĮĸéģĹ产
    0.26
    loses
    0.25
    ?type
    0.25
    Ã¤ÃŁ
    0.25
    æѤæĸĩ
    0.24
    hma
    0.24
    ább
    0.24
    åıĹä¸įäºĨ
    0.24
    èħ¿éĥ¨
    0.24
    åĽłåħ¶
    0.23
    Activations Density 5.986%

    No Known Activations