© 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. 20-TRANSCODER-HP
    7. 140614
    Prev
    Next
    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    terra
    -0.24
    acet
    -0.24
    ï¼īï¼Į
    -0.24
    ORB
    -0.24
    ))),
    -0.24
    ”),
    -0.24
    ropa
    -0.23
     mắc
    -0.23
    suma
    -0.23
    cco
    -0.23
    POSITIVE LOGITS
    irm
    0.28
    èµĦè´¨
    0.26
    åĨįæĿ¥
    0.25
    ä¸Ģä¼ļ
    0.25
    ä¸įèĥ½åĨį
    0.25
    åħī
    0.24
    åħ³åĪĩ
    0.24
    IBAction
    0.24
    nameof
    0.24
     Há»ĵ
    0.24
    Activations Density 35.186%

    No Known Activations