© 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. 140827
    Prev
    Next
    INDEX
    Explanations

    health and food

    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
    åIJĪä½ľ
    -0.28
     Colo
    -0.26
     prób
    -0.25
    é¼ĵèĪŀ
    -0.25
    Bre
    -0.24
    èµı
    -0.24
    umar
    -0.24
     insert
    -0.24
    è±ģ
    -0.24
     Bre
    -0.24
    POSITIVE LOGITS
    æ®ĸ
    0.25
    _named
    0.24
    logg
    0.24
     Option
    0.24
    çĶ¸
    0.24
    å¤§åĽ½
    0.24
     possibility
    0.24
    æīĢ以æĪij们
    0.23
    å²Ľ
    0.23
    æľīæĿĥ
    0.23
    Activations Density 8.226%

    No Known Activations