© 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. 142698
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    iele
    -0.27
     açık
    -0.26
     bordered
    -0.25
    åĬĪ
    -0.25
    Palindrome
    -0.24
    rc
    -0.24
    大æĪĺ
    -0.24
     Açık
    -0.24
    æļ´åĬĽ
    -0.24
    thin
    -0.24
    POSITIVE LOGITS
    both
    0.45
     both
    0.44
    Both
    0.43
     BOTH
    0.42
     Both
    0.40
    _both
    0.36
    scheme
    0.31
    _BOTH
    0.28
    èħ°éĥ¨
    0.28
     nuts
    0.28
    Activations Density 24.039%

    No Known Activations