© 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. 129086
    Prev
    Next
    INDEX
    Explanations

    and

    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
     diy
    -0.27
     re
    -0.27
     res
    -0.26
     control
    -0.25
     independent
    -0.25
     unordered
    -0.25
     respectively
    -0.24
     ret
    -0.24
     di
    -0.24
     Control
    -0.24
    POSITIVE LOGITS
    &);↵
    0.27
    å¥ijæľº
    0.26
    æīĴ
    0.26
    fg
    0.25
     particulars
    0.25
    &)↵
    0.25
    emale
    0.25
    æŀķ
    0.24
    ++)↵
    0.24
    æļ¨
    0.24
    Activations Density 23.677%

    No Known Activations