© 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. 140726
    Prev
    Next
    INDEX
    Explanations

    Technical writing/questions

    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
    izabeth
    -0.27
    hos
    -0.26
     disb
    -0.25
    atk
    -0.24
    æIJŀ好
    -0.24
    /ws
    -0.24
    igrams
    -0.23
    æķĪèĥ½
    -0.23
    uits
    -0.23
    ç«£
    -0.23
    POSITIVE LOGITS
    类似çļĦ
    0.38
     similarly
    0.34
    âĨ©
    0.32
    æľīè¿Ļæł·çļĦ
    0.31
     »↵↵
    0.29
    ä¹Łæĺ¯å¦ĤæѤ
    0.29
    »↵↵
    0.28
    pper
    0.27
     similar
    0.27
    .rect
    0.26
    Activations Density 77.348%

    No Known Activations