© 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. 130948
    Prev
    Next
    INDEX
    Explanations

    medicine or computers

    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
    amus
    -0.27
     conc
    -0.27
     Conc
    -0.25
    ten
    -0.25
    etic
    -0.24
    :selected
    -0.24
     Decre
    -0.24
    -selected
    -0.24
    èĬ·
    -0.23
     decrease
    -0.23
    POSITIVE LOGITS
     [[[
    0.30
    åľºä¸Ĭ
    0.29
    bove
    0.24
    pies
    0.24
    é«ĺä»·
    0.24
    马åĬĽ
    0.24
    OTA
    0.24
    ä¸įæŃ»
    0.23
    ÅĤow
    0.23
    ibo
    0.23
    Activations Density 2.202%

    No Known Activations