© 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. 130786
    Prev
    Next
    INDEX
    Explanations

    inhalers, medicine

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Bayesian
    -0.26
     Barb
    -0.25
    âĺij
    -0.25
    ,rp
    -0.24
    沫
    -0.24
    sharp
    -0.24
    æĦŁäºº
    -0.24
     vac
    -0.23
    åĵ®
    -0.23
     Robbins
    -0.23
    POSITIVE LOGITS
     ru
    0.31
    icz
    0.28
     umo
    0.28
    å°Ķ
    0.26
    olian
    0.24
    æĺİ
    0.24
    åĩĢ
    0.24
    ioctl
    0.24
     decrement
    0.24
    é¢Ĩåıĸ
    0.23
    Activations Density 6.717%

    No Known Activations