© 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. 108702
    Prev
    Next
    INDEX
    Explanations

    Beginning clauses/sentences

    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
    mgr
    -0.29
    ÐĺÐĿ
    -0.26
    RAW
    -0.26
    饮水
    -0.26
     Tribune
    -0.24
    Ĥ¨
    -0.24
    ĸī
    -0.24
    OWN
    -0.23
     mó
    -0.23
    -bar
    -0.23
    POSITIVE LOGITS
    ä¸įæĸŃå®ĮåĸĦ
    0.25
    éĩįçĤ¹
    0.25
    akes
    0.24
    _PRINT
    0.24
    .press
    0.24
     retired
    0.24
    åįĥéĩĮ
    0.23
    ProgressDialog
    0.23
    ernet
    0.23
     collaps
    0.23
    Activations Density 18.533%

    No Known Activations