© 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. 142751
    Prev
    Next
    INDEX
    Explanations

    Descriptions or specifications

    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
    })",
    -0.29
    åī¯å±Ģéķ¿
    -0.27
    館
    -0.27
    é«¡
    -0.26
    å¸ĺ
    -0.26
     ÙĪاÙĦس
    -0.26
    åī¯ä¸»ä»»
    -0.25
    aging
    -0.24
    æĿIJ
    -0.24
    riors
    -0.24
    POSITIVE LOGITS
    óc
    0.28
    -fat
    0.25
    é»ĺå¥ij
    0.24
    bjerg
    0.23
    .tap
    0.23
     hanging
    0.23
     pastoral
    0.23
    inn
    0.23
     held
    0.23
    æįĮ
    0.22
    Activations Density 8.163%

    No Known Activations