© 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. 62663
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
     "
    -0.29
    eral
    -0.28
    ä¸Ģè½®
    -0.28
    ŀĭ
    -0.26
    çĶ²
    -0.25
     gal
    -0.25
    æľŁ
    -0.25
    ippers
    -0.25
    Reviewer
    -0.25
     entry
    -0.24
    POSITIVE LOGITS
    ubo
    0.28
    CJK
    0.26
    /port
    0.26
    ç»ıèIJ¥æ´»åĬ¨
    0.26
    ä¼Ĭæĸ¯
    0.25
    adro
    0.25
    .leadingAnchor
    0.25
     Sadd
    0.24
     programme
    0.24
     TJ
    0.24
    Activations Density 63.783%

    No Known Activations