© 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. 62702
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    living
    -0.27
    iving
    -0.27
    éments
    -0.26
    _ASSUME
    -0.26
    èĬ¸
    -0.25
    ardi
    -0.24
     num
    -0.24
    arded
    -0.24
     living
    -0.24
    ç´łè´¨
    -0.24
    POSITIVE LOGITS
    orney
    0.27
    ä¸įç¡®å®ļæĢ§
    0.25
     обоÑĢ
    0.24
    å¤ļä½į
    0.23
    Tomorrow
    0.23
     Inspired
    0.23
    ="{!!
    0.23
     khá»ıi
    0.23
     wir
    0.23
     Patton
    0.23
    Activations Density 1.524%

    No Known Activations