© 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. 64684
    Prev
    Next
    INDEX
    Explanations

    one

    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
    anz
    -0.29
    tant
    -0.28
    OrDefault
    -0.26
    éĢ»è¾ij
    -0.26
    士
    -0.26
    tur
    -0.26
    gz
    -0.25
     sideline
    -0.25
    .actor
    -0.24
    logical
    -0.24
    POSITIVE LOGITS
    äºĴèģĶ
    0.27
    å¾Ĺä¸įåĪ°
    0.26
     reinstall
    0.26
    ä¸įå¼Ģ
    0.26
    è°ĥåĬ¨
    0.25
     bif
    0.25
    缸
    0.24
     sắp
    0.24
    äºĴ
    0.24
     p
    0.24
    Activations Density 0.796%

    No Known Activations