© 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. 142777
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ainment
    -0.28
    æĬĢèĥ½åŁ¹è®Ń
    -0.28
    ÙĨس
    -0.27
    Rem
    -0.26
    -ups
    -0.26
    æľīæķĪçļĦ
    -0.26
    rador
    -0.25
    aning
    -0.24
    Training
    -0.23
     %(
    -0.23
    POSITIVE LOGITS
    plx
    0.28
    æ½Ń
    0.27
     extreme
    0.27
    åĨł
    0.27
     Cla
    0.26
     minus
    0.26
     tack
    0.25
    ç³Ĭ
    0.25
    VML
    0.25
    oten
    0.24
    Activations Density 22.181%

    No Known Activations