© 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. 54684
    Prev
    Next
    INDEX
    Explanations

    scientific research on antigens

    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
     surface
    -0.31
     surf
    -0.29
    surface
    -0.29
    (surface
    -0.29
    Surface
    -0.28
    éĿ¢
    -0.28
     Surface
    -0.28
    表éĿ¢
    -0.27
    surf
    -0.27
     superf
    -0.27
    POSITIVE LOGITS
     bound
    0.30
    bound
    0.29
     exposes
    0.28
    bud
    0.28
    -coded
    0.27
    纰
    0.27
    coded
    0.27
    _pi
    0.27
    aic
    0.27
     el
    0.26
    Activations Density 0.075%

    No Known Activations