© 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. 140745
    Prev
    Next
    INDEX
    Explanations

    Relating to hands

    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
    quad
    -0.26
    tha
    -0.25
    åī¯ç§ĺ书éķ¿
    -0.24
    cam
    -0.24
     functools
    -0.24
    Quad
    -0.23
    æ¡ī
    -0.23
     добÑĢо
    -0.23
    æĻĤéĸĵãĤĴ
    -0.23
     Bliss
    -0.23
    POSITIVE LOGITS
    ä¹Łæľīå¾Īå¤ļ
    0.25
     Phar
    0.25
    ä¸ŃåĽ½å¤§éĻĨ
    0.24
    çħİ
    0.24
    jected
    0.24
     expected
    0.24
    wers
    0.24
    æĭİ
    0.24
    åĨħå¤ĸ
    0.24
    _pad
    0.23
    Activations Density 1.480%

    No Known Activations