© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53831
    Prev
    Next
    INDEX
    Explanations

    medical emergencies

    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
    Not in Any Lists

    No Comments

    Negative Logits
     broadcasting
    -0.27
    åķĨåºĹ
    -0.27
    werk
    -0.27
    assy
    -0.26
     d
    -0.26
     cache
    -0.23
     curses
    -0.23
    öst
    -0.23
    paged
    -0.23
     Pager
    -0.23
    POSITIVE LOGITS
    rete
    0.28
    reek
    0.28
    éħįæĸĻ
    0.28
    积水
    0.27
    Second
    0.26
     tension
    0.25
    second
    0.25
    éĹ´æİ¥
    0.25
    ç½¹
    0.25
    atables
    0.25
    Activations Density 0.006%

    No Known Activations