© 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. 64761
    Prev
    Next
    INDEX
    Explanations

    code/symbols

    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
    bsites
    -0.29
    ç«ĭä½ĵ
    -0.29
     ones
    -0.28
    _same
    -0.26
    unch
    -0.25
    themes
    -0.25
    bserv
    -0.24
    bs
    -0.24
    .CreateInstance
    -0.24
    æĸ°æµªè´¢ç»ı
    -0.24
    POSITIVE LOGITS
    åıĹ伤
    0.30
    evin
    0.28
     dut
    0.27
    kest
    0.26
     Suff
    0.25
     Unterstüt
    0.25
     unfavor
    0.25
    Violation
    0.25
    åħ¥åĽŃ
    0.24
    [param
    0.24
    Activations Density 1.977%

    No Known Activations