© 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. 142667
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĶ¶æķĽ
    -0.26
     Merkel
    -0.25
    icip
    -0.25
    icator
    -0.24
    felt
    -0.24
     //~
    -0.24
    ặt
    -0.24
    гон
    -0.24
    cy
    -0.24
    irit
    -0.23
    POSITIVE LOGITS
    BorderStyle
    0.29
    丰满
    0.28
    ä¸ĢçĶŁ
    0.28
    çµĤãĤıãĤĬ
    0.26
    森æŀĹåħ¬åĽŃ
    0.25
     Strawberry
    0.25
    rafted
    0.24
    å°Ĭ严
    0.24
    åĬłæ²¹ç«Ļ
    0.24
    ãĤĭãģĵãģ¨ãģ¯
    0.23
    Activations Density 8.987%

    No Known Activations

    This feature has no known activations.