© 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. 130903
    Prev
    Next
    INDEX
    Explanations

    Technology and industry

    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
    orado
    -0.28
    ìŀIJëıĻ
    -0.25
    .ld
    -0.25
    quoted
    -0.25
    acias
    -0.25
    触åĬ¨
    -0.25
    ières
    -0.25
    å®ĮåĸĦçļĦ
    -0.25
    ÑĢÑĥб
    -0.24
    sequ
    -0.24
    POSITIVE LOGITS
    ombat
    0.26
    Spread
    0.26
    vu
    0.25
    æĮĩå®ļ
    0.25
     dau
    0.25
    æ£Ĥ
    0.25
    thon
    0.25
    ours
    0.24
    æĹ¶è¡¨ç¤º
    0.24
    mv
    0.24
    Activations Density 23.863%

    No Known Activations