© 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. 32-TRANSCODER-HP
    7. 44046
    Prev
    Next
    INDEX
    Explanations

    Diseases and infections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĭľ
    -0.29
    NW
    -0.27
     fries
    -0.27
     bew
    -0.26
    Caps
    -0.26
    caps
    -0.26
    -Men
    -0.25
     infect
    -0.25
    åĬłå¼ºå¯¹
    -0.25
     habitat
    -0.24
    POSITIVE LOGITS
    im
    0.28
    ilater
    0.28
    ill
    0.28
    imas
    0.27
     Ill
    0.27
    -il
    0.26
    å¯Ł
    0.25
    åŀ«
    0.24
    åĴ¯
    0.24
    RUN
    0.24
    Activations Density 0.003%

    No Known Activations