© 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. 129173
    Prev
    Next
    INDEX
    Explanations

    Acronyms/Abbreviations

    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
    dale
    -0.32
    skirts
    -0.26
    lations
    -0.26
    folio
    -0.25
    <article
    -0.25
    dashboard
    -0.24
    urement
    -0.24
    å±ħ
    -0.24
    icut
    -0.23
    folk
    -0.23
    POSITIVE LOGITS
    `.`
    0.28
    æĶ¾å¤§
    0.26
    注
    0.25
     Meth
    0.25
     leak
    0.25
    éĤ£ä¸Ģ
    0.25
    cast
    0.24
    åħĪ导
    0.24
    casts
    0.24
     consisted
    0.24
    Activations Density 30.088%

    No Known Activations