© 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. 108523
    Prev
    Next
    INDEX
    Explanations

    chemistry/biological experiments

    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
    çĨĬ
    -0.28
    _verbose
    -0.26
    çİĩ为
    -0.25
    æģ©
    -0.25
    ç¼ł
    -0.24
     Sand
    -0.23
     einz
    -0.23
    æĪijä»¬çŁ¥éģĵ
    -0.23
    ç»Ĩç»Ĩ
    -0.23
    æ²Ļ
    -0.23
    POSITIVE LOGITS
    rotein
    0.34
     bacterial
    0.27
    ircraft
    0.26
    ivor
    0.26
     desi
    0.25
    uced
    0.25
     Redistributions
    0.24
    åĪĽ
    0.24
     yell
    0.24
     Bicycle
    0.23
    Activations Density 8.217%

    No Known Activations