© 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. 131135
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
     .$
    -0.27
    '}}↵
    -0.26
     submitting
    -0.26
    è¿ĺæĥ³
    -0.26
    údo
    -0.25
    èī²ç´ł
    -0.24
    '}}
    -0.24
    ocode
    -0.24
    ()}}↵
    -0.24
    ä¹Łå¸ĮæľĽ
    -0.24
    POSITIVE LOGITS
    ickle
    0.29
    istr
    0.27
     lif
    0.27
     Brid
    0.27
    br
    0.27
    å²IJ
    0.27
    isi
    0.26
    grams
    0.26
    bill
    0.26
     millennium
    0.26
    Activations Density 34.781%

    No Known Activations