© 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. 33-TRANSCODER-HP
    7. 52532
    Prev
    Next
    INDEX
    Explanations

    infection and antibiotics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zn
    -0.28
    ett
    -0.27
    lay
    -0.27
    ©
    -0.26
     salty
    -0.25
     crisp
    -0.25
     crunchy
    -0.25
    æĭĽ
    -0.24
     crispy
    -0.24
    Gal
    -0.24
    POSITIVE LOGITS
    æĦŁæŁĵ
    0.40
    ä¼łæŁĵ
    0.40
    èıĮ
    0.37
     bacter
    0.36
    æĿĢèıĮ
    0.35
     infectious
    0.34
    otics
    0.33
     infect
    0.33
     antibiot
    0.32
    çĸ«
    0.32
    Activations Density 0.073%

    No Known Activations