© 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. 142567
    Prev
    Next
    INDEX
    Explanations

    Prices, costs, and goods

    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
     Compatibility
    -0.30
     Mang
    -0.28
    Compatibility
    -0.28
     ageing
    -0.27
    compat
    -0.26
     compatibility
    -0.26
    åħ¼å®¹
    -0.25
     Aging
    -0.25
     Awareness
    -0.24
     orientations
    -0.24
    POSITIVE LOGITS
     costs
    0.51
    å¤ļå°ijéĴ±
    0.45
     kosten
    0.45
    æĪIJæľ¬
    0.45
    è´¹çĶ¨
    0.45
     cost
    0.43
    éĩijé¢Ŀ
    0.42
    çļĦæĪIJæľ¬
    0.42
     Costs
    0.41
     budget
    0.40
    Activations Density 73.870%

    No Known Activations