© 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. 131081
    Prev
    Next
    INDEX
    Explanations

    call

    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
    ä¾į
    -0.27
     hứng
    -0.27
    ë¥ĺ
    -0.26
    çĴĨ
    -0.26
     pat
    -0.25
    acz
    -0.24
    agens
    -0.24
    åıĺçİ°
    -0.24
    iens
    -0.24
    Ø´ÙĪ
    -0.23
    POSITIVE LOGITS
     gre
    0.29
    ä¸ŃåĽ½æĶ¿åºľ
    0.26
    å±Ĭæ¯ķä¸ļçĶŁ
    0.25
    Cpp
    0.25
    åľ¨ä¸ŃåĽ½
    0.25
    DTV
    0.24
    udder
    0.24
    gre
    0.24
    ä¸ŃåĽ½å¤§éĻĨ
    0.23
     rings
    0.23
    Activations Density 8.191%

    No Known Activations