© 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. 106850
    Prev
    Next
    INDEX
    Explanations

    articles (the, a)

    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
     deal
    -0.30
    Deal
    -0.29
    å±ķ
    -0.28
     Tucker
    -0.27
     punct
    -0.27
    illis
    -0.26
    Contin
    -0.26
    /packages
    -0.25
     WARRANTIES
    -0.24
     abs
    -0.24
    POSITIVE LOGITS
    çĴ°
    0.28
     Smoke
    0.24
     Bank
    0.24
    éħĴåIJ§
    0.23
     Beauty
    0.23
    >{↵
    0.23
    ober
    0.23
    ÑĦÑĢ
    0.23
    quisitions
    0.23
    axe
    0.23
    Activations Density 31.667%

    No Known Activations